Publications
Search
Laird, John E.; Lebiere, Christian; Rosenbloom, Paul S.
In: AI Magazine, vol. 38, no. 4, pp. 13, 2017, ISSN: 0738-4602, 0738-4602.
@article{laird_standard_2017,
title = {A Standard Model of the Mind: Toward a Common Computational Framework across Artificial Intelligence, Cognitive Science, Neuroscience, and Robotics},
author = {John E. Laird and Christian Lebiere and Paul S. Rosenbloom},
url = {https://search.proquest.com/docview/1987347010?pq-origsite=gscholar},
doi = {10.1609/aimag.v38i4.2744},
issn = {0738-4602, 0738-4602},
year = {2017},
date = {2017-12-01},
journal = {AI Magazine},
volume = {38},
number = {4},
pages = {13},
abstract = {The purpose of this article is to begin the process of engaging the international research community in developing what can be called a standard model of the mind, where the mind we have in mind here is human-like. The notion of a standard model has its roots in physics, where over more than a half-century the international community has developed and tested a standard model that combines much of what is known about particles. This model is assumed to be internally consistent, yet still have major gaps. Its function is to serve as a cumulative reference point for the field while also driving efforts to both extend and break it.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Rizzo, Albert; Roy, Michael J.; Hartholt, Arno; Costanzo, Michelle; Highland, Krista Beth; Jovanovic, Tanja; Norrholm, Seth D.; Reist, Chris; Rothbaum, Barbara; Difede, JoAnn
Virtual Reality Applications for the Assessment and Treatment of PTSD Book Section
In: Handbook of Military Psychology, pp. 453–471, Springer International Publishing, Cham, Switzerland, 2017, ISBN: 978-3-319-66190-2 978-3-319-66192-6.
@incollection{rizzo_virtual_2017,
title = {Virtual Reality Applications for the Assessment and Treatment of PTSD},
author = {Albert Rizzo and Michael J. Roy and Arno Hartholt and Michelle Costanzo and Krista Beth Highland and Tanja Jovanovic and Seth D. Norrholm and Chris Reist and Barbara Rothbaum and JoAnn Difede},
url = {http://link.springer.com/10.1007/978-3-319-66192-6_27},
doi = {10.1007/978-3-319-66192-6_27},
isbn = {978-3-319-66190-2 978-3-319-66192-6},
year = {2017},
date = {2017-12-01},
booktitle = {Handbook of Military Psychology},
pages = {453–471},
publisher = {Springer International Publishing},
address = {Cham, Switzerland},
abstract = {War is one of the most challenging situations that a human being can encounter. The physical, emotional, cognitive, and psychological demands of a combat environment place tremendous stress on even the most well-prepared military people. It is no surprise that the stressful experiences, characteristics of operations in Iraq and Afghanistan, have produced significant numbers of service members (SMs) and veterans at risk for posttraumatic stress disorder (PTSD), as well as other psychosocial/behavioral health conditions. For example, as of June 2015, the Defense Medical Surveillance System reported 138,197 active duty SMs had been diagnosed with PTSD (Fischer, 2015). In a meta-analysis of studies published since 2001, 13.2% of infantry service members met the criteria for PTSD, with incidence rising dramatically to 25–30% in units with high levels of direct combat exposure (Kok, Herrell, Thomas, & Hoge, 2012). Moreover, as of early 2013, the prevalence of PTSD among discharged veterans receiving treatment at Veteran Affairs (VA) clinics was reported to be 29% (Fischer, 2013). These findings make a compelling case for a continued focus on developing and enhancing the availability of diverse evidence- based treatment options to address this military behavioral healthcare challenge. One emerging area of research and clinical focus is of the use of Virtual Reality (VR) simulation technology as a tool for delivering evidence-based approaches for the assessment and treatment of PTSD. Although in recent times, the popular media has lavishly reported on VR’s potential impact on all elements of our evolving digital culture, and has created the impression that VR is a novel technology, the reality is that VR is not a new concept, and many of its developmental roots are traceable to the 1980s and 1990s (Schnipper et al., 2015). Moreover, a large scientific literature has emerged over the last 20 years demonstrating the unique and added value that is accrued with the use of VR to address a wide range of clinical health conditions (Rizzo 1994; Rizzo et al., 1997; 2002; 2010; 2014; Rizzo, Cukor et al., 2015). Within that context, the present chapter will summarize the ways that researchers and clinicians have employed VR to create relevant simulations that can be applied to the assessment and treatment of PTSD.},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
Roemmele, Melissa; Gordon, Andrew S.
Lexical preferences in an automated story writing system Proceedings Article
In: Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, 2017.
@inproceedings{roemmele_lexical_2017,
title = {Lexical preferences in an automated story writing system},
author = {Melissa Roemmele and Andrew S. Gordon},
url = {http://people.ict.usc.edu/ gordon/publications/NIPS-WS17},
year = {2017},
date = {2017-12-01},
booktitle = {Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS 2017)},
address = {Long Beach, CA},
abstract = {The field of artificial intelligence has long envisioned the ability of computers to automatically write stories (Dehn [1981], Lebowitz [1985], Meehan [1977], Turner [1993]). For a long time, progress on this task was limited by the difficulty of encoding the vast narrative knowledge needed to produce stories with diverse content. The rise of data-driven approaches to AI introduced the opportunity to acquire this knowledge automatically from story corpora. Since then, this approach has been utilized to generate narratives for different domains and genres (Li et al. [2013], McIntyre and Lapata [2009]), which has in turn made it possible for systems to collaborate with human authors in developing stories (Khalifa et al. [2017], Manjavacas et al. [2017], Swanson and Gordon [2012]). Roemmele and Gordon [2015] introduced a web-based application called Creative Help that provides automated assistance for writing stories. The interface consists of a text box where users type “textbackslashtextbackslashtextbackslashtextbackslashhelptextbackslashtextbackslashtextbackslashtextbackslash” to automatically generate a suggestion for the next sentence in the story. One novelty of the application is that it tracks users’ modifications to the suggestions, which enables the original and modified form of a suggestion to be compared. This enables sentences generated by different models to be comparatively evaluated in terms of their influence on the story. We examined a dataset of 1182 Creative Help interactions produced by a total of 139 authors, where each interaction consists of the generated suggestion and the author’s corresponding modification. The suggestions were generated by a Recurrent Neural Network language model (RNN LM), as described in Roemmele et al. [2017], which generates sentences by iteratively sampling words according to their observed probability in a corpus. The training corpus for the model analyzed here was 8032 books (a little over half a billion words) in the BookCorpus1, which contains freely available fiction from a variety of genres. This paper briefly characterizes the generated sentences by highlighting their most prominent words and phrases and showing examples of them in context.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Rizzo, Albert
Ethically Aligned Design, Version 2 Book
IEEE, 2017.
@book{rizzo_ethically_2017,
title = {Ethically Aligned Design, Version 2},
author = {Albert Rizzo},
url = {https://standards.ieee.org/industry-connections/ec/ead-v1.html},
year = {2017},
date = {2017-12-01},
publisher = {IEEE},
abstract = {Intelligent and autonomous technical systems are specifically designed to reduce human intervention in our day-to-day lives. In so doing, these new fields are raising concerns about their impact on individuals and societies. Current discussions include advocacy for the positive impact, as well as warnings, based on the potential harm to privacy, discrimination, loss of skills, economic impacts, security of critical infrastructure, and the long-term effects on social well-being. Because of their nature, the full benefit of these technologies will be attained only if they are aligned with our defined values and ethical principles. We must therefore establish frameworks to guide and inform dialogue and debate around the non-technical implications of these technologies.},
keywords = {},
pubstate = {published},
tppubtype = {book}
}
Bunt, Harry; Petukhova, Volha; Traum, David; Alexandersson, Jan
Dialogue Act Annotation with the ISO 24617-2 Standard Book Section
In: Multimodal Interaction with W3C Standards, pp. 109–135, Springer International Publishing, Cham, Switzerland, 2017, ISBN: 978-3-319-42814-7 978-3-319-42816-1.
@incollection{bunt_dialogue_2017,
title = {Dialogue Act Annotation with the ISO 24617-2 Standard},
author = {Harry Bunt and Volha Petukhova and David Traum and Jan Alexandersson},
url = {http://link.springer.com/10.1007/978-3-319-42816-1_6},
isbn = {978-3-319-42814-7 978-3-319-42816-1},
year = {2017},
date = {2017-11-01},
booktitle = {Multimodal Interaction with W3C Standards},
pages = {109–135},
publisher = {Springer International Publishing},
address = {Cham, Switzerland},
abstract = {This chapter describes recent and ongoing annotation efforts using the ISO 24617-2 standard for dialogue act annotation. Experimental studies are reported on the annotation by human annotators and by annotation machines of some of the specific features of the ISO annotation scheme, such as its multidimensional annotation of communicative functions, the recognition of each of its nine dimensions, and the recognition of dialogue act qualifiers for certainty, conditionality, and sentiment. The construction of corpora of dialogues, annotated according to ISO 24617-2, is discussed, including the recent DBOX and DialogBank corpora.},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
Thomas, Jerald; Azmandian, Mahdi; Grunwald, Sonia; Le, Donna; Krum, David; Kang, Sin-Hwa; Rosenberg, Evan Suma
Effects of Personalized Avatar Texture Fidelity on Identity Recognition in Virtual Reality Proceedings Article
In: Proceedings of ICAT-EGVE 2017 - International Conference on Artificial Reality and Telexistence and Eurographics Symposium on Virtual Environments, The Eurographics Association, Adelaide, Australia, 2017, ISBN: 978-3-03868-038-3.
@inproceedings{thomas_effects_2017,
title = {Effects of Personalized Avatar Texture Fidelity on Identity Recognition in Virtual Reality},
author = {Jerald Thomas and Mahdi Azmandian and Sonia Grunwald and Donna Le and David Krum and Sin-Hwa Kang and Evan Suma Rosenberg},
url = {https://diglib.eg.org/handle/10.2312/egve20171345},
doi = {10.2312/egve.20171345},
isbn = {978-3-03868-038-3},
year = {2017},
date = {2017-11-01},
booktitle = {Proceedings of ICAT-EGVE 2017 - International Conference on Artificial Reality and Telexistence and Eurographics Symposium on Virtual Environments},
publisher = {The Eurographics Association},
address = {Adelaide, Australia},
abstract = {Recent advances in 3D scanning, reconstruction, and animation techniques have made it possible to rapidly create photorealistic avatars based on real people. While it is now possible to create personalized avatars automatically with consumer-level technology, their visual fidelity still falls far short of 3D avatars created with professional cameras and manual artist effort. To evaluate the importance of investing resources in the creation of high-quality personalized avatars, we conducted an experiment to investigate the effects of varying their visual texture fidelity, specifically focusing on identity recognition of specific individuals. We designed two virtual reality experimental scenarios: (1) selecting a specific avatar from a virtual lineup and (2) searching for an avatar in a virtual crowd. Our results showed that visual fidelity had a significant impact on participants’ abilities to identify specific avatars from a lineup wearing a head-mounted display. We also investigated gender effects for both the participants and the confederates from which the avatars were created.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Neubauer, Catherine; Chollet, Mathieu; Mozgai, Sharon; Dennison, Mark; Khooshabeh, Peter; Scherer, Stefan
The relationship between task-induced stress, vocal changes, and physiological state during a dyadic team task Proceedings Article
In: Proceedings of the 19th ACM International Conference on Multimodal Interaction, pp. 426–432, ACM Press, Glasgow, UK, 2017, ISBN: 978-1-4503-5543-8.
@inproceedings{neubauer_relationship_2017,
title = {The relationship between task-induced stress, vocal changes, and physiological state during a dyadic team task},
author = {Catherine Neubauer and Mathieu Chollet and Sharon Mozgai and Mark Dennison and Peter Khooshabeh and Stefan Scherer},
url = {http://dl.acm.org/citation.cfm?doid=3136755.3136804},
doi = {10.1145/3136755.3136804},
isbn = {978-1-4503-5543-8},
year = {2017},
date = {2017-11-01},
booktitle = {Proceedings of the 19th ACM International Conference on Multimodal Interaction},
pages = {426–432},
publisher = {ACM Press},
address = {Glasgow, UK},
abstract = {It is commonly known that a relationship exists between the human voice and various emotional states. Past studies have demonstrated changes in a number of vocal features, such as fundamental frequency f0 and peakSlope, as a result of varying emotional state. These voice characteristics have been shown to relate to emotional load, vocal tension, and, in particular, stress. Although much research exists in the domain of voice analysis, few studies have assessed the relationship between stress and changes in the voice during a dyadic team interaction. The aim of the present study was to investigate the multimodal interplay between speech and physiology during a high-workload, high-stress team task. Specifically, we studied task-induced effects on participants' vocal signals, specifically, the f0 and peakSlope features, as well as participants' physiology, through cardiovascular measures. Further, we assessed the relationship between physiological states related to stress and changes in the speaker's voice. We recruited participants with the specific goal of working together to diffuse a simulated bomb. Half of our sample participated in an "Ice Breaker" scenario, during which they were allowed to converse and familiarize themselves with their teammate prior to the task, while the other half of the sample served as our "Control". Fundamental frequency (f0), peakSlope, physiological state, and subjective stress were measured during the task. Results indicated that f0 and peakSlope significantly increased from the beginning to the end of each task trial, and were highest in the last trial, which indicates an increase in emotional load and vocal tension. Finally, cardiovascular measures of stress indicated that the vocal and emotional load of speakers towards the end of the task mirrored a physiological state of psychological "threat".},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Swanson, Reid William; Gordon, Andrew S.; Khooshabeh, Peter; Sagae, Kenji; Huskey, Richard; Mangus, Michael; Amir, Ori; Weber, Rene
An Empirical Analysis of Subjectivity and Narrative Levels in Weblog Storytelling Across Cultures Journal Article
In: Dialogue & Discourse, vol. 8, no. 2, pp. 105–128, 2017.
@article{swanson_empirical_2017,
title = {An Empirical Analysis of Subjectivity and Narrative Levels in Weblog Storytelling Across Cultures},
author = {Reid William Swanson and Andrew S. Gordon and Peter Khooshabeh and Kenji Sagae and Richard Huskey and Michael Mangus and Ori Amir and Rene Weber},
url = {https://www.researchgate.net/publication/321170929_An_Empirical_Analysis_of_Subjectivity_and_Narrative_Levels_in_Personal_Weblog_Storytelling_Across_Cultures?_sg=Ck1pqxhW1uuTUe54DX5BLVYey6L6DkwTpjnes1ctAEuGQDHxoEOr887eKWjHIA0_-kk4ya9dXwEZ4OM},
doi = {10.5087/dad.2017.205},
year = {2017},
date = {2017-11-01},
journal = {Dialogue & Discourse},
volume = {8},
number = {2},
pages = {105–128},
abstract = {Storytelling is a universal activity, but the way in which discourse structure is used to persuasively convey ideas and emotions may depend on cultural factors. Because first-person accounts of life experiences can have a powerful impact in how a person is perceived, the storyteller may instinctively employ specific strategies to shape the audience’s perception. Hypothesizing that some of the differences in storytelling can be captured by the use of narrative levels and subjectivity, we analyzed over one thousand narratives taken from personal weblogs. First, we compared stories from three different cultures written in their native languages: English, Chinese and Farsi. Second, we examined the impact of these two discourse properties on a reader’s attitude and behavior toward the narrator. We found surprising similarities and differences in how stories are structured along these two dimensions across cultures. These discourse properties have a small but significant impact on a reader’s behavioral response toward the narrator.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Cychosz, Margaret; Gordon, Andrew S.; Odimegwu, Obiageli; Connolly, Olivia; Bellassai, Jenna; Roemmele, Melissa
Effective Scenario Designs for Free-Text Interactive Fiction Proceedings Article
In: Proceedings of the International Conference on Interactive Digital Storytelling, pp. 12–23, Springer International Publishing, Funchal Madeira, Portugal, 2017.
@inproceedings{cychosz_effective_2017,
title = {Effective Scenario Designs for Free-Text Interactive Fiction},
author = {Margaret Cychosz and Andrew S. Gordon and Obiageli Odimegwu and Olivia Connolly and Jenna Bellassai and Melissa Roemmele},
url = {https://link.springer.com/chapter/10.1007/978-3-319-71027-3_2},
doi = {10.1007/978-3-319-71027-3_2},
year = {2017},
date = {2017-11-01},
booktitle = {Proceedings of the International Conference on Interactive Digital Storytelling},
pages = {12–23},
publisher = {Springer International Publishing},
address = {Funchal Madeira, Portugal},
abstract = {Free-text interactive fiction allows players to narrate the actions of protagonists via natural language input, which are automatically directed to appropriate storyline outcomes using natural language processing techniques. We describe an authoring platform called the Data-driven Interactive Narrative Engine (DINE), which supports free-text interactive fiction by connecting player input to authored outcomes using unsupervised text classification techniques based on text corpus statistics. We hypothesize that the coherence of the interaction, as judged by the players of a DINE scenario, is dependent on specific design choices made by the author. We describe three empirical experiments with crowdsourced subjects to investigate how authoring choices impacted the coherence of the interaction, finding that scenario design and writing style can predict significant differences.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Rosario, Dalton; Borel, Christoph; Conover, Damon; McAlinden, Ryan; Ortiz, Anthony; Shiver, Sarah; Simon, Blair
Small Drone Field Experiment: Data Collection & Processing Journal Article
In: NATO SET-241 Symposium, 2017.
@article{rosario_small_2017,
title = {Small Drone Field Experiment: Data Collection & Processing},
author = {Dalton Rosario and Christoph Borel and Damon Conover and Ryan McAlinden and Anthony Ortiz and Sarah Shiver and Blair Simon},
url = {https://arxiv.org/abs/1711.10693},
year = {2017},
date = {2017-11-01},
journal = {NATO SET-241 Symposium},
abstract = {Following an initiative formalized in April 2016—formally known as ARL West—between the U.S. Army Research Laboratory (ARL) and University of Southern California’s Institute for Creative Technologies (USC ICT), a field experiment was coordinated and executed in the summer of 2016 by ARL, USC ICT, and Headwall Photonics. The purpose was to image part of the USC main campus in Los Angeles, USA, using two portable COTS (commercial off the shelf) aerial drone solutions for data acquisition, for photogrammetry (3D reconstruction from images), and fusion of hyperspectral data with the recovered set of 3D point clouds representing the target area. The research aims for determining the viability of having a machine capable of segmenting the target area into key material classes (e.g., manmade structures, live vegetation, water) for use in multiple purposes, to include providing the user with a more accurate scene understanding and enabling the unsupervised automatic sampling of meaningful material classes from the target area for adaptive semi-supervised machine learning. In the latter, a target-set library may be used for automatic machine training with data of local material classes, as an example, to increase the prediction chances of machines recognizing targets. The field experiment and associated data post processing approach to correct for reflectance, geo-rectify, recover the area’s dense point clouds from images, register spectral with elevation properties of scene surfaces from the independently collected datasets, and generate the desired scene segmented maps are discussed. Lessons learned from the experience are also highlighted throughout the paper.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Nye, Benjamin D; Kaimakis, Nicholas J; Krishnamachari, Madhusudhan; Swartout, William; Campbell, Julia; Anderson, Clinton; Davis, Dan M
MentorPal: Interactive Virtual Mentors Based on Real-Life STEM Professionals Proceedings Article
In: Proceedings of the Interservice/Industry Training, Simulation and Education Conference (I/ITSEC) 2017, a2z, Inc., Orlando, Florida, 2017.
@inproceedings{nye_mentorpal_2017,
title = {MentorPal: Interactive Virtual Mentors Based on Real-Life STEM Professionals},
author = {Benjamin D Nye and Nicholas J Kaimakis and Madhusudhan Krishnamachari and William Swartout and Julia Campbell and Clinton Anderson and Dan M Davis},
url = {http://www.iitsecdocs.com/search},
year = {2017},
date = {2017-11-01},
booktitle = {Proceedings of the Interservice/Industry Training, Simulation and Education Conference (I/ITSEC) 2017},
publisher = {a2z, Inc.},
address = {Orlando, Florida},
abstract = {In an ideal world, all students could meet STEM role models as they explore different careers. However, events such as career fairs do not scale well: professionals have limited time and effective mentors are not readily available in all fields. The result is that students’ understanding is minimal about what professionals in STEM fields do every day, what education is needed, and even what STEM fields exist. Moreover, since in-person interactions rely on finding people engaged in current STEM careers, students may form career goals for stagnant fields rather than growing fields (e.g., projected workforce needs). To address this problem, we are designing a scalable tablet-based app that gives students the opportunity to converse with interactive recordings of real-life STEM professionals. These conversational virtual agents will emulate a question-and-answer session with STEM professionals who have Navy ties and who are engaging, enthusiastic, and effective mentors. These interactions will allow students to have a lifelike informational interview with a virtual agent whose responses are directly drawn from a specific real professional’s video-recorded interview. This work differs from prior research on career guides by capturing the experiences of a collection of unique mentors, which should be more authentic and engaging than a generic agent or resource which speaks only about the average experience. This paper will discuss the process of creating the first such virtual STEM mentor prototype, including the development of an extensive mentoring question bank (approximately 500 questions); key mentoring topics that intersect STEM, DoD, and civilian life; techniques for cost-effective recording of remote mentors; and the process of training and verifying a natural language dialogue model for answering and suggesting career questions. Finally, we conclude with implications, strengths, and drawbacks of virtualizing the experience of talking with specific mentors, from the perspectives of efficacy, scalability, and maintainability.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Rosenbloom, Paul S.
Lessons from Mapping Sigma onto the Standard Model of the Mind: Self-Monitoring, Memory/Learning, and Symbols Proceedings Article
In: Proceedings of the AAAI 2017 Fall Symposium on A Standard Model of the Mind, AAAI, Arlington, VA, 2017.
@inproceedings{rosenbloom_lessons_2017,
title = {Lessons from Mapping Sigma onto the Standard Model of the Mind: Self-Monitoring, Memory/Learning, and Symbols},
author = {Paul S. Rosenbloom},
url = {https://aaai.org/ocs/index.php/FSS/FSS17/paper/view/15947},
year = {2017},
date = {2017-11-01},
booktitle = {Proceedings of the AAAI 2017 Fall Symposium on A Standard Model of the Mind},
publisher = {AAAI},
address = {Arlington, VA},
abstract = {Sigma was one of the three architectures explicitly factored into the recent development of the standard model of the mind. Here we dig deeper into the mapping of Sigma onto the standard model begun there to explore three lessons that illustrate outstanding “issues” with the current standard model while providing food for thought for its future development.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Prasad, Keshav; Briet, Kayla; Odimegwu, Obiageli; Connolly, Olivia; Gonzalez, Diego; Gordon, Andrew S.
“The Long Walk” From Linear Film to Interactive Narrative Proceedings Article
In: Proceedings of the 10th International Workshop on Intelligent Narrative Technologies (INT10), AAAI, Snowbird, Utah, 2017.
@inproceedings{prasad_long_2017,
title = {“The Long Walk” From Linear Film to Interactive Narrative},
author = {Keshav Prasad and Kayla Briet and Obiageli Odimegwu and Olivia Connolly and Diego Gonzalez and Andrew S. Gordon},
url = {http://people.ict.usc.edu/ gordon/publications/INT17B},
year = {2017},
date = {2017-10-01},
booktitle = {Proceedings of the 10th International Workshop on Intelligent Narrative Technologies (INT10)},
publisher = {AAAI},
address = {Snowbird, Utah},
abstract = {Advances in hardware and software for virtual reality and 360-degree video afford new opportunities for immersive digital storytelling, but also pose new challenges as players seek an increased sense of meaningful agency in fictional storyworlds. In this paper, we explore the interaction designs afforded by voice-controlled interactive narratives, where players speak their intended actions when prompted at choice points in branching storylines. We describe seven interaction design patterns that balance the player’s need for meaningful agency with an author’s goal to present an intended storyline. We argue that these structural designs are orthogonal to the content of a story, such that any particular story may be effectively restructured to use different patterns. By way of demonstration, we describe our efforts to remix and restructure a 360-degree film entitled The Long Walk, transforming it from a largely linear narrative with minimal interactivity into a voice-controlled interactive narrative with meaningful player agency.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Ringeval, Fabien; Schuller, Björn; Valstar, Michel; Gratch, Jonathan; Cowie, Roddy; Pantic, Maja
Summary for AVEC 2017: Real-life Depression and Affect Challenge and Workshop Proceedings Article
In: Proceedings of the 2017 ACM on Multimedia Conference, pp. 1963–1964, ACM Press, Mountain View, CA, 2017, ISBN: 978-1-4503-4906-2.
@inproceedings{ringeval_summary_2017,
title = {Summary for AVEC 2017: Real-life Depression and Affect Challenge and Workshop},
author = {Fabien Ringeval and Björn Schuller and Michel Valstar and Jonathan Gratch and Roddy Cowie and Maja Pantic},
url = {http://dl.acm.org/citation.cfm?doid=3123266.3132049},
doi = {10.1145/3123266.3132049},
isbn = {978-1-4503-4906-2},
year = {2017},
date = {2017-10-01},
booktitle = {Proceedings of the 2017 ACM on Multimedia Conference},
pages = {1963–1964},
publisher = {ACM Press},
address = {Mountain View, CA},
abstract = {The seventh Audio-Visual Emotion Challenge and workshop AVEC 2017 was held in conjunction with ACM Multimedia'17. This year, the AVEC series addresses two distinct sub-challenges: emotion recognition and depression detection. The Affect Sub-Challenge is based on a novel dataset of human-human interactions recorded 'in-the-wild', whereas the Depression Sub-Challenge is based on the same dataset as the one used in AVEC 2016, with human-agent interactions. In this summary, we mainly describe participation and its conditions.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Stratou, Giota; Schalk, Job Van Der; Hoegen, Rens; Gratch, Jonathan
Refactoring Facial Expressions: an Automatic Analysis of Natural Occurring Facial Expressions in Iterative Social Dilemma Proceedings Article
In: Proceedings of the 7th International Conference on Affective Computing and Intelligent Interaction, San Antonio, TX, 2017.
@inproceedings{stratou_refactoring_2017,
title = {Refactoring Facial Expressions: an Automatic Analysis of Natural Occurring Facial Expressions in Iterative Social Dilemma},
author = {Giota Stratou and Job Van Der Schalk and Rens Hoegen and Jonathan Gratch},
url = {http://ict.usc.edu/pubs/Refactoring%20Facial%20Expressions-an%20Automatic%20Analysis%20of%20Natural%20Occurring%20Facial.pdf},
year = {2017},
date = {2017-10-01},
booktitle = {Proceedings of the 7th International Conference on Affective Computing and Intelligent Interaction},
address = {San Antonio, TX},
abstract = {Many automatic facial expression recognizers now output individual facial action units (AUs), but several lines of evidence suggest that it is the combination of AUs that is psychologically meaningful: e.g., (a) constraints arising from facial morphology, (b) prior published evidence, (c) claims arising from basic emotion theory. We performed factor analysis on a large data set and recovered factors that have been discussed in the literature as psychologically meaningful. Further we show that some of these factors have external validity in that they predict participant behaviors in an iterated prisoner’s dilemma task and in fact with more precision than the individual AUs. These results both reinforce the validity of automatic recognition (as these factors would be expected from accurate AU detection) and suggest the benefits of using such factors for understanding these facial expressions as social signals.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Stratou, Giota; Hoegen, Rens; Lucas, Gale; Gratch, Jonathan
Investigating Gender Differences in Temporal Dynamics during an Iterated Social Dilemma: an Automatic Analysis Using Networks Proceedings Article
In: Proceedings of the 7th International Conference on Affective Computing and Intelligent Interaction, San Antonio, TX, 2017.
@inproceedings{stratou_investigating_2017,
title = {Investigating Gender Differences in Temporal Dynamics during an Iterated Social Dilemma: an Automatic Analysis Using Networks},
author = {Giota Stratou and Rens Hoegen and Gale Lucas and Jonathan Gratch},
url = {http://ict.usc.edu/pubs/Investigating%20Gender%20Differences%20in%20Temporal%20Dynamics%20during%20an%20Iterated%20Social.pdf},
year = {2017},
date = {2017-10-01},
booktitle = {Proceedings of the 7th International Conference on Affective Computing and Intelligent Interaction},
address = {San Antonio, TX},
abstract = {Emotions have a temporal nature and very often personality traits and underlying psychological conditions are hidden in the dynamics of those expressions. Within this work, we investigate the dynamics of the facial displays of dyads during an iterated social dilemma. We focus on the effect of gender and gender-pairing on those behaviors. We use networks to capture the temporal dynamics and create measures of inter- and intra- personal dependencies of emotional states. Our analysis on an iterated prisoner’s dilemma corpus suggests that there are gender differences on the transitions of the emotional states and the degree of emotional influence from the opponent.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Treanor, Mike; Warren, Nicholas; Reed, Mason; Smith, Adam M.; Ortiz, Pablo; Carney, Laurel; Sherman, Loren; Carré, Elizabeth; Vivatvisha, Nadya; Harrell, D. Fox; Mardo, Paola; Gordon, Andrew; Dormans, Joris; Robison, Barrie; Gomez, Spencer; Heck, Samantha; Wright, Landon; Soule, Terence
Playable Experiences at AIIDE 2017 Proceedings Article
In: Proceedings of The Thirteenth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE-17), Association for the Advancement of Artificial Intelligence, Snowbird, Utah, 2017.
@inproceedings{treanor_playable_2017,
title = {Playable Experiences at AIIDE 2017},
author = {Mike Treanor and Nicholas Warren and Mason Reed and Adam M. Smith and Pablo Ortiz and Laurel Carney and Loren Sherman and Elizabeth Carré and Nadya Vivatvisha and D. Fox Harrell and Paola Mardo and Andrew Gordon and Joris Dormans and Barrie Robison and Spencer Gomez and Samantha Heck and Landon Wright and Terence Soule},
url = {https://pdfs.semanticscholar.org/19f9/a76f6edcc6aa41bf19dba017da8c1c01e2b3.pdf},
year = {2017},
date = {2017-10-01},
booktitle = {Proceedings of The Thirteenth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE-17)},
publisher = {Association for the Advancement of Artificial Intelligence},
address = {Snowbird, Utah},
abstract = {This paper describes the accepted entries to the fifth Playable Experiences track to be held at the AIIDE conference. The Playable Experiences track showcases complete works that make use of artificial intelligence techniques as an integral part of the player experience.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Tsang, Michael; Korolik, Vadim; Scherer, Stefan; Matarić, Maja
Comparing models for gesture recognition of children's bullying behaviors Proceedings Article
In: Affective Computing and Intelligent Interaction (ACII), 2017 Seventh International Conference on, pp. 138–145, IEEE, San Antonio, TX, 2017.
@inproceedings{tsang_comparing_2017,
title = {Comparing models for gesture recognition of children's bullying behaviors},
author = {Michael Tsang and Vadim Korolik and Stefan Scherer and Maja Matarić},
url = {https://ieeexplore.ieee.org/abstract/document/8273591/},
doi = {10.1109/ACII.2017.8273591},
year = {2017},
date = {2017-10-01},
booktitle = {Affective Computing and Intelligent Interaction (ACII), 2017 Seventh International Conference on},
pages = {138–145},
publisher = {IEEE},
address = {San Antonio, TX},
abstract = {We explored gesture recognition applied to the problem of classifying natural physical bullying behaviors by children. To capture natural bullying behavior data, we developed a humanoid robot that used hand-coded gesture recognition to identify basic physical bullying gestures and responded by explaining why the gestures were inappropriate. Children interacted with the robot by trying various bullying behaviors, thereby allowing us to collect a natural bullying behavior dataset for training the classifiers. We trained three different sequence classifiers using the collected data and compared their effectiveness at classifying different types of common physical bullying behaviors. Overall, Hidden Conditional Random Fields achieved the highest average F1 score (0.645) over all tested gesture classes.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Rizzo, Albert “Skip”; Koenig, Sebastian Thomas
Is clinical virtual reality ready for primetime? Journal Article
In: Neuropsychology, vol. 31, no. 8, pp. 877–899, 2017, ISSN: 1931-1559, 0894-4105.
@article{rizzo_is_2017,
title = {Is clinical virtual reality ready for primetime?},
author = {Albert “Skip” Rizzo and Sebastian Thomas Koenig},
url = {https://www.researchgate.net/publication/319165844_Is_Clinical_Virtual_Reality_Ready_for_Primetime},
doi = {10.1037/neu0000405},
issn = {1931-1559, 0894-4105},
year = {2017},
date = {2017-10-01},
journal = {Neuropsychology},
volume = {31},
number = {8},
pages = {877–899},
abstract = {Objective: Since the mid-1990s, a significant scientific literature has evolved regarding the outcomes from the use of what we now refer to as Clinical Virtual Reality (VR). This use of VR simulation technology has produced encouraging results when applied to address cognitive, psychological, motor, and functional impairments across a wide range of clinical health conditions. This article addresses the question, “Is Clinical VR Ready for Primetime?” Method: After a brief description of the various forms of VR technology, we discuss the trajectory of Clinical VR over the last 20 years and summarize the basic assets that VR offers for creating clinical applications. The discussion then addresses the question of readiness in terms of the theoretical basis for Clinical VR assets, the research to date, the pragmatic factors regarding availability, usability, and costs of Clinical VR content/systems, and the ethical issues for the safe use of VR with clinical populations. Results: Our review of the theoretical underpinnings and research findings to date leads to the prediction that Clinical VR will have a significant impact on future research and practice. Pragmatic issues that can influence adoption across many areas of psychology also appear favorable, but professional guidelines will be needed to promote its safe and ethical use. Conclusions: While there is still much research needed to advance the science in this area, we strongly believe that Clinical VR applications will become indispensable tools in the toolbox of psychological researchers and practitioners and will only grow in relevance and popularity in the future. Keywords: Clinical Virtual Reality, Psychology, Rehabilitation, Neuropsychology},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Narang, Sahil; Best, Andrew; Shapiro, Ari; Manocha, Dinesh
Generating Virtual Avatars with Personalized Walking Gaits using Commodity Hardware Proceedings Article
In: Proceedings of the on Thematic Workshops of ACM Multimedia 2017 - Thematic Workshops '17, pp. 219–227, ACM Press, Mountain View, California, USA, 2017, ISBN: 978-1-4503-5416-5.
@inproceedings{narang_generating_2017,
title = {Generating Virtual Avatars with Personalized Walking Gaits using Commodity Hardware},
author = {Sahil Narang and Andrew Best and Ari Shapiro and Dinesh Manocha},
url = {http://dl.acm.org/citation.cfm?doid=3126686.3126766},
doi = {10.1145/3126686.3126766},
isbn = {978-1-4503-5416-5},
year = {2017},
date = {2017-10-01},
booktitle = {Proceedings of the on Thematic Workshops of ACM Multimedia 2017 - Thematic Workshops '17},
pages = {219–227},
publisher = {ACM Press},
address = {Mountain View, California, USA},
abstract = {We present a novel algorithm for generating virtual avatars which move like the represented human subject, using inexpensive sensors & commodity hardware. Our algorithm is based on a perceptual study that evaluates self-recognition and similarity of gaits rendered on virtual avatars. We identify discriminatory features of human gait and propose a data-driven synthesis algorithm that can generate a set of similar gaits from a single walker. These features are combined to automatically synthesize personalized gaits for a human user from noisy motion capture data. The overall approach is robust and can generate new gaits with little or no artistic intervention using commodity sensors in a simple laboratory setting. We demonstrate our approach's application in rapidly animating virtual avatars of new users with personalized gaits, as well as procedurally generating distinct but similar "families" of gait in virtual environments.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Filter
2009
Morie, Jacquelyn; El-Nasr, Magy Seif; Drachen, Anders
A Scientific Look at the Design of Aesthetically and Emotionally Engaging Interactive Entertainment Experiences Book Section
In: Affective Computing and Interaction: Psychological, Cognitive and Neuroscientific Perspectives, 2009.
Abstract | Links | BibTeX | Tags:
@incollection{morie_scientific_2009,
title = {A Scientific Look at the Design of Aesthetically and Emotionally Engaging Interactive Entertainment Experiences},
author = {Jacquelyn Morie and Magy Seif El-Nasr and Anders Drachen},
url = {http://ict.usc.edu/pubs/Emotional%20Affordances%20within%20Interactive%20Experiences-%20A%20scientific%20approach%20to%20understanding%20artistic%20tools%20for%20stimulating%20emotions%20within%20Interactive%20Entertainment%20Experiences.pdf},
year = {2009},
date = {2009-12-01},
booktitle = {Affective Computing and Interaction: Psychological, Cognitive and Neuroscientific Perspectives},
abstract = {The interactive entertainment industry has become a multi-billion dollar industry with revenues overcom- ing those of the movie industry (ESA, 2009). Beyond the demand for high fidelity graphics or stylized imagery, participants in these environments have come to expect certain aesthetic and artistic qualities that engage them at a very deep emotional level. These qualities pertain to the visual aesthetic, dramatic structure, pacing, and sensory systems embedded within the experience. All these qualities are carefully crafted by the creator of the interactive experience to evoke affect. In this book chapter, the authors will attempt to discuss the design techniques developed by artists to craft such emotionally engaging experi- ences. In addition, they take a scientific approach whereby we discuss case studies of the use of these design techniques and experiments that attempt to validate their use in stimulating emotions.},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
Fyffe, Graham; Wilson, Cyrus A.; Debevec, Paul
Cosine Lobe Based Relighting from Gradient Illumination Photographs Proceedings Article
In: Conference on Visual Media Production, London, UK, 2009.
Abstract | Links | BibTeX | Tags: Graphics
@inproceedings{fyffe_cosine_2009,
title = {Cosine Lobe Based Relighting from Gradient Illumination Photographs},
author = {Graham Fyffe and Cyrus A. Wilson and Paul Debevec},
url = {http://www.ict.usc.edu/pubs/Cosine%20Lobe%20Based%20Relighting%20from%20Gradient%20Illumination%20Photographs.pdf},
year = {2009},
date = {2009-11-01},
booktitle = {Conference on Visual Media Production},
address = {London, UK},
abstract = {We present an image-based method for relighting a scene by analytically fitting a cosine lobe to the reflectance function at each pixel, based on gradient illumination pho- tographs. Realistic relighting results for many materials are obtained using a single per-pixel cosine lobe obtained from just two color photographs: one under uniform white illumi- nation and the other under colored gradient illumination. For materials with wavelength-dependent scattering, a better fit can be obtained using independent cosine lobes for the red, green, and blue channels, obtained from three monochromatic gradient illumination conditions instead of the colored gradient condition. We explore two cosine lobe reflectance functions, both of which allow an analytic fit to the gradient conditions. One is non-zero over half the sphere of lighting directions, which works well for diffuse and specular materials, but fails for materials with broader scattering such as fur. The other is non-zero everywhere, which works well for broadly scattering materials and still produces visually plausible results for diffuse and specular materials. Additionally, we estimate scene geometry from the photometric normals to produce hard shadows cast by the geometry, while still reconstructing the input photographs exactly.},
keywords = {Graphics},
pubstate = {published},
tppubtype = {inproceedings}
}
Alexander, Oleg; Rogers, Mike; Lambeth, William; Chiang, Matt; Debevec, Paul
Creating a Photoreal Digital Actor: The Digital Emily Project Proceedings Article
In: IEEE European Conference on Visual Media Production (CVMP), London, UK, 2009.
Abstract | Links | BibTeX | Tags: Graphics
@inproceedings{alexander_creating_2009,
title = {Creating a Photoreal Digital Actor: The Digital Emily Project},
author = {Oleg Alexander and Mike Rogers and William Lambeth and Matt Chiang and Paul Debevec},
url = {https://dl.acm.org/doi/pdf/10.1145/1667239.1667251},
year = {2009},
date = {2009-11-01},
booktitle = {IEEE European Conference on Visual Media Production (CVMP)},
number = {ICT TR 04 2009},
address = {London, UK},
institution = {University of Southern California Institute for Creative Technologies},
abstract = {The Digital Emily Project is a collaboration between facial animation company Image Metrics and the Graphics Laboratory at the University of Southern California's Institute for Creative Technologies to achieve one of the world's first photorealistic digital facial performances. The project leverages latest-generation techniques in high-resolution face scanning, character rigging, video-based facial animation, and compositing. An actress was first filmed on a studio set speaking emotive lines of dialog in high definition. The lighting on the set was captured as a high dynamic range light probe image. The actress' face was then three-dimensionally scanned in thirty-three facial expressions showing different emotions and mouth and eye movements using a high-resolution facial scanning process accurate to the level of skin pores and fine wrinkles. Lighting-independent diffuse and specular reflectance maps were also acquired as part of the scanning process. Correspondences between the 3D expression scans were formed using a semi-automatic process, allowing a blendshape facial animation rig to be constructed whose expressions closely mirrored the shapes observed in the rich set of facial scans; animated eyes and teeth were also added to the model. Skin texture detail showing dynamic wrinkling was converted into multiresolution displacement maps also driven by the blend shapes. A semi-automatic video-based facial animation system was then used to animate the 3D face rig to match the performance seen in the original video, and this performance was tracked onto the facial motion in the studio video. The final face was illuminated by the captured studio illumination and shading using the acquired reflectance maps with a skin translucency shading algorithm. Using this process, the project was able to render a synthetic facial performance which was generally accepted as being a real face.},
keywords = {Graphics},
pubstate = {published},
tppubtype = {inproceedings}
}
Pütten, Astrid M.; Krämer, Nicole; Gratch, Jonathan
Who Is there? Can a Virtual Agent Really Elicit Social Presence? Proceedings Article
In: The 12th Annual International Workshop on Presence, Los Angeles, CA, 2009.
Abstract | Links | BibTeX | Tags: Virtual Humans
@inproceedings{von_der_puitten_who_2009,
title = {Who Is there? Can a Virtual Agent Really Elicit Social Presence?},
author = {Astrid M. Pütten and Nicole Krämer and Jonathan Gratch},
url = {http://ict.usc.edu/pubs/whosthere.pdf},
year = {2009},
date = {2009-11-01},
booktitle = {The 12th Annual International Workshop on Presence},
address = {Los Angeles, CA},
abstract = {This study investigates whether humans perceive a higher degree of social presence when interacting with an animated character that displays natural as opposed to no listening behaviors and whether this interacts with people's believe that they are interacting with an agent or an avatar. In a 2x2 between subjects experimental design 83 participants were either made believe that they encounter an agent, or that they communicate with another participant mediated by an avatar. In fact, in both conditions the communication partner was an autonomous agent that either exhibited high or low behavioral realism. We found that participants experienced equal amounts of presence, regardless of interacting with an agent or an avatar. Behavioral realism, however, had an impact on the subjective feeling of presence: people confronted with a character displaying high behavioral realism reported a higher degree of mutual awareness.},
keywords = {Virtual Humans},
pubstate = {published},
tppubtype = {inproceedings}
}
Rosenbloom, Paul S.
Towards Uniform Implementation of Architectural Diversity Proceedings Article
In: Proceedings of the AAAI Fall Symposium on Multi-Representational Architectures for Human-Level Intelligence, 2009.
Abstract | Links | BibTeX | Tags: CogArch, Cognitive Architecture, Virtual Humans
@inproceedings{rosenbloom_towards_2009-1,
title = {Towards Uniform Implementation of Architectural Diversity},
author = {Paul S. Rosenbloom},
url = {http://ict.usc.edu/pubs/Towards%20Uniform%20Implementation%20of%20Architectural%20Diversity.pdf},
year = {2009},
date = {2009-11-01},
booktitle = {Proceedings of the AAAI Fall Symposium on Multi-Representational Architectures for Human-Level Intelligence},
abstract = {Multi-representational architectures exploit diversity to yield the breadth of capabilities required for intelligent behavior in the world, but in so doing can sacrifice too much of the complementary benefits of architectural uniformity. The proposal here is to couple the benefits of diversity and uniformity through establishment of a uniform graph-based implementation level for diverse architectures.},
keywords = {CogArch, Cognitive Architecture, Virtual Humans},
pubstate = {published},
tppubtype = {inproceedings}
}
Han, Kyu J.; Narayanan, Shrikanth
Signature Cluster Model Selection for Incremental Gaussian Mixture Cluster Modeling in Agglomerative Hierarchical Speaker Clustering Proceedings Article
In: Proceedings of Interspeech 2009, Brighton, UK, 2009.
Abstract | Links | BibTeX | Tags:
@inproceedings{han_signature_2009,
title = {Signature Cluster Model Selection for Incremental Gaussian Mixture Cluster Modeling in Agglomerative Hierarchical Speaker Clustering},
author = {Kyu J. Han and Shrikanth Narayanan},
url = {http://ict.usc.edu/pubs/Signature%20Cluster%20Model%20Selection.pdf},
year = {2009},
date = {2009-10-01},
booktitle = {Proceedings of Interspeech 2009},
address = {Brighton, UK},
abstract = {Agglomerative hierarchical speaker clustering (AHSC) has been widely used for classifying speech data by speaker charac- teristics. Its bottom-up, one-way structure of merging the clos- est cluster pair at every recursion step, however, makes it diffi- cult to recover from incorrect merging. Hence, making AHSC robust to incorrect merging is an important issue. In this pa- per we address this problem in the framework of AHSC based on incremental Gaussian mixture models, which we previously introduced for better representing variable cluster size. Specif- ically, to minimize contamination in cluster models by hetero- geneous data, we select and keep updating a representative (or signature) model for each cluster during AHSC. Experiments on meeting speech excerpts (4 hours total) verify that the proposed approach improves average speaker clustering performance by approximately 20% (relative).},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Kalinli, Ozlem; Sundaram, Shiva; Narayanan, Shrikanth
Saliency-Driven Unstructured Acoustic Scene Classification Using Latent Perceptual Indexing Proceedings Article
In: Proceedings of IEEE MMSP, Rio de Janeiro, Brazil, 2009.
Abstract | Links | BibTeX | Tags:
@inproceedings{kalinli_saliency-driven_2009,
title = {Saliency-Driven Unstructured Acoustic Scene Classification Using Latent Perceptual Indexing},
author = {Ozlem Kalinli and Shiva Sundaram and Shrikanth Narayanan},
url = {http://ict.usc.edu/pubs/Saliency-Driven%20Unstructured%20Acoustic%20Scene%20Classification%20Using%20Latent%20Perceptual%20Indexing.pdf},
year = {2009},
date = {2009-10-01},
booktitle = {Proceedings of IEEE MMSP},
address = {Rio de Janeiro, Brazil},
abstract = {Automatic acoustic scene classification of real life, complex and unstructured acoustic scenes is a challenging task as the number of acoustic sources present in the audio stream are unknown and overlapping in time. In this work, we present a novel approach to classification such unstructured acoustic scenes. Motivated by the bottom-up attention model of the human auditory system, salient events of an audio clip are extracted in an unsupervised manner and presented to the classification system. Similar to latent semantic indexing of text documents, the classi- fication system uses unit-document frequency measure to index the clip in a continuous, latent space. This allows for developing a completely class-independent approach to audio classification. Our results on the BBC sound effects library indicates that using the saliency-driven attention selection approach presented in this paper, 17.5% relative improvement can be obtained in frame-based classification and 25% relative improvement can be obtained using the latent audio indexing approach.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Sridhar, Vivek Kumar Rangarajan; Bangalore, Srinivas; Narayanan, Shrikanth
Combining lexical, syntactic and prosodic cues for improved online dialog act tagging Journal Article
In: Computer Speech and Language, vol. 23, no. 4, pp. 407–422, 2009.
Abstract | Links | BibTeX | Tags:
@article{sridhar_combining_2009,
title = {Combining lexical, syntactic and prosodic cues for improved online dialog act tagging},
author = {Vivek Kumar Rangarajan Sridhar and Srinivas Bangalore and Shrikanth Narayanan},
url = {http://ict.usc.edu/pubs/Combining%20lexical,%20syntactic%20and%20prosodic%20cues%20for%20improved%20online%20dialog%20act%20tagging.pdf},
year = {2009},
date = {2009-10-01},
journal = {Computer Speech and Language},
volume = {23},
number = {4},
pages = {407–422},
abstract = {Prosody is an important cue for identifying dialog acts. In this paper, we show that modeling the sequence of acoustic– prosodic values as n-gram features with a maximum entropy model for dialog act (DA) tagging can perform better than conventional approaches that use coarse representation of the prosodic contour through summative statistics of the prosodic contour. The proposed scheme for exploiting prosody results in an absolute improvement of 8.7% over the use of most other widely used representations of acoustic correlates of prosody. The proposed scheme is discriminative and exploits context in the form of lexical, syntactic and prosodic cues from preceding discourse segments. Such a decoding scheme facilitates online DA tagging and offers robustness in the decoding process, unlike greedy decoding schemes that can potentially propagate errors. Our approach is different from traditional DA systems that use the entire conversation for offine dialog act decoding with the aidofa discourse model.In contrast, we use only static features and approximate the previous dialog act tags in terms of lexical, syntactic and prosodic information extracted from previous utterances. Experiments on the Switchboard-DAMSL corpus, using only lexical, syntactic and prosodic cues from three previous utterances, yield a DA tagging accuracy of 72% compared to the best case scenario with accurate knowledge of previous DA tags (oracle), which results in 74% accuracy. © 2009 Elsevier Ltd. All rights reserved.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Kalinli, Ozlem; Narayanan, Shrikanth
Continuous Speech Recognition Using Attention Shift Decoding with Soft Decision Proceedings Article
In: Proceedings of Interspeech 2009, Brighton, UK, 2009.
Abstract | Links | BibTeX | Tags:
@inproceedings{kalinli_continuous_2009,
title = {Continuous Speech Recognition Using Attention Shift Decoding with Soft Decision},
author = {Ozlem Kalinli and Shrikanth Narayanan},
url = {http://ict.usc.edu/pubs/Continuous%20Speech%20Recognition%20Using%20Attention%20Shift%20Decoding%20with%20Soft%20Decision.pdf},
year = {2009},
date = {2009-10-01},
booktitle = {Proceedings of Interspeech 2009},
address = {Brighton, UK},
abstract = {We present an attention shift decoding (ASD) method inspired by human speech recognition. In contrast to the traditional auto- matic speech recognition (ASR) systems, ASD decodes speech inconsecutively using reliability criteria; the gaps (unreliable speech regions) are decoded with the evidence of islands (reli- able speech regions). On the BU Radio News Corpus, ASD pro- vides significant improvement (2.9% absolute) over the baseline ASR results when it is used with oracle island-gap informa- tion. At the core of the ASD method is the automatic island- gap detection. Here, we propose a new feature set for automatic island-gap detection which achieves 83.7% accuracy. To cope with the imperfect nature of the island-gap classification, we also propose a new ASD algorithm using soft decision. The ASD with soft decision provides 0.4% absolute (2.2% relative) improvement over the baseline ASR results when it is used with automatically detected islands and gaps.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Lee, Jina; Marsella, Stacy C.; Prendinger, Helmut; Neviarouskaya, Alena
Learning a Model of Speaker Head Nods using Gesture Corpora Proceedings Article
In: International Conference on Autonomous Agents and Multiagent Systems (AAMAS), Budapest, Hungary, 2009.
Abstract | Links | BibTeX | Tags: Social Simulation
@inproceedings{lee_learning_2009-1,
title = {Learning a Model of Speaker Head Nods using Gesture Corpora},
author = {Jina Lee and Stacy C. Marsella and Helmut Prendinger and Alena Neviarouskaya},
url = {http://ict.usc.edu/pubs/learning%20a%20model%20of%20speaker%20head%20nods.pdf},
year = {2009},
date = {2009-10-01},
booktitle = {International Conference on Autonomous Agents and Multiagent Systems (AAMAS)},
address = {Budapest, Hungary},
abstract = {During face-to-face conversation, the speaker's head is continually in motion. These movements serve a variety of important communicative functions, and may also be influ- enced by our emotions. The goal for this work is to build a domain-independent model of speaker's head movements and investigate the effect of using affective information dur- ing the learning process. Once the model is learned, it can later be used to generate head movements for virtual agents. In this paper, we describe our machine-learning approach to predict speaker's head nods using an annotated corpora of face-to-face human interaction and emotion labels gener- ated by an affect recognition model. We describe the feature selection process, training process, and the comparison of results of the learned models under varying conditions. The results show that using affective information can help pre- dict head nods better than when no affective information is used.},
keywords = {Social Simulation},
pubstate = {published},
tppubtype = {inproceedings}
}
Sagae, Kenji
Analysis of Discourse Structure with Syntactic Dependencies and Data-Driven Shift-Reduce Parsing Proceedings Article
In: International Conference on Parsing Technologies (IWPT-09), Paris, France, 2009.
Abstract | Links | BibTeX | Tags:
@inproceedings{sagae_analysis_2009,
title = {Analysis of Discourse Structure with Syntactic Dependencies and Data-Driven Shift-Reduce Parsing},
author = {Kenji Sagae},
url = {http://ict.usc.edu/pubs/Analysis%20of%20discourse%20structure.pdf},
year = {2009},
date = {2009-10-01},
booktitle = {International Conference on Parsing Technologies (IWPT-09)},
address = {Paris, France},
abstract = {We present an efficient approach for discourse parsing within and across sentences, where the unit of processing is an entire document, and not a single sentence. We apply shift-reduce algorithms for dependency and constituent parsing to determine syntactic dependencies for the sentences in a document, and subsequently a Rhetorical Structure Theory (RST) tree for the entire document. Our results show that our linear-time shift-reduce framework achieves high accuracy and a large improvement in efficiency compared to a state-of-the-art approach based on chart parsing with dynamic programming.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Sagae, Kenji; Gordon, Andrew S.
Clustering Words by Syntactic Similarity Improves Dependency Parsing of Predicate-Argument Structures Proceedings Article
In: International Conference on Parsing Technologies (IWPT-09), Paris, France, 2009.
Abstract | Links | BibTeX | Tags: The Narrative Group, Virtual Humans
@inproceedings{sagae_clustering_2009,
title = {Clustering Words by Syntactic Similarity Improves Dependency Parsing of Predicate-Argument Structures},
author = {Kenji Sagae and Andrew S. Gordon},
url = {http://ict.usc.edu/pubs/Clustering%20Words%20by%20Syntactic%20Similarity%20Improves%20Dependency%20Parsing%20of%20Predicate-Argument%20Structures.pdf},
year = {2009},
date = {2009-10-01},
booktitle = {International Conference on Parsing Technologies (IWPT-09)},
address = {Paris, France},
abstract = {We present an approach for deriving syntactic word clusters from parsed text, grouping words according to their unlexicalized syntactic contexts. We then explore the use of these syntactic clusters in leveraging a large corpus of trees generated by a high-accuracy parser to improve the accuracy of another parser based on a different formalism for representing a different level of sentence structure. In our experiments, we use phrase-structure trees to produce syntactic word clusters that are used by a predicate-argument dependency parser, significantly improving its accuracy.},
keywords = {The Narrative Group, Virtual Humans},
pubstate = {published},
tppubtype = {inproceedings}
}
DeVault, David; Sagae, Kenji; Traum, David
Can I finish? Learning when to respond to incremental interpretation results in interactive dialogue Proceedings Article
In: 10th SIGdial Workshop on Discourse and Dialogue, London, UK, 2009.
Abstract | Links | BibTeX | Tags: Virtual Humans
@inproceedings{devault_can_2009,
title = {Can I finish? Learning when to respond to incremental interpretation results in interactive dialogue},
author = {David DeVault and Kenji Sagae and David Traum},
url = {http://ict.usc.edu/pubs/Can%20I%20%EF%AC%81nish%20Learning%20when%20to%20respond%20to%20incremental%20interpretation%20results%20in%20interactive%20dialogue.pdf},
year = {2009},
date = {2009-09-01},
booktitle = {10th SIGdial Workshop on Discourse and Dialogue},
address = {London, UK},
abstract = {We investigate novel approaches to responsive overlap behaviors in dialogue systems, opening possibilities for systems to interrupt, acknowledge or complete a user’s utterance while it is still in progress. Our specific contributions are a method for determining when a system has reached a point of maximal understanding of an ongoing user utterance, and a prototype implementation that shows how systems can use this ability to strategically initiate system completions of user utterances. More broadly, this framework facilitates the implementation of a range of overlap behaviors that are common in human dialogue, but have been largely absent in dialogue systems.},
keywords = {Virtual Humans},
pubstate = {published},
tppubtype = {inproceedings}
}
Lee, Chi-Chun; Busso, Carlos; Lee, Sungbok; Narayanan, Shrikanth
Modeling Mutual Influence of Interlocutor Emotion States in Dyadic Spoken Interactions Proceedings Article
In: Proceedings of Interspeech 2009, Brighton, UK, 2009.
Abstract | Links | BibTeX | Tags:
@inproceedings{lee_modeling_2009,
title = {Modeling Mutual Influence of Interlocutor Emotion States in Dyadic Spoken Interactions},
author = {Chi-Chun Lee and Carlos Busso and Sungbok Lee and Shrikanth Narayanan},
url = {http://ict.usc.edu/pubs/Modeling%20Mutual%20Influence%20of%20Interlocutor%20Emotion%20States%20in%20Dyadic%20Spoken%20Interactions.pdf},
year = {2009},
date = {2009-09-01},
booktitle = {Proceedings of Interspeech 2009},
address = {Brighton, UK},
abstract = {In dyadic human interactions, mutual influence - a person's in- fluence on the interacting partner's behaviors - is shown to be important and could be incorporated into the modeling frame- work in characterizing, and automatically recognizing the par- ticipants' states. We propose a Dynamic Bayesian Network (DBN) to explicitly model the conditional dependency between two interacting partners' emotion states in a dialog using data from the IEMOCAP corpus of expressive dyadic spoken in- teractions. Also, we focus on automatically computing the Valence-Activation emotion attributes to obtain a continuous characterization of the participants' emotion flow. Our pro- posed DBN models the temporal dynamics of the emotion states as well as the mutual influence between speakers in a dialog. With speech based features, the proposed network improves classification accuracy by 3.67% absolute and 7.12% relative over the Gaussian Mixture Model (GMM) baseline on isolated turn-by-turn emotion classification.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Tsiartas, Andreas; Ghosh, Prasanta Kumar; Georgiou, Panayiotis G.; Narayanan, Shrikanth
Context-driven automatic bilingual movie subtitle alignment Proceedings Article
In: Proceedings of Interspeech 2009, Brighton, UK, 2009.
Abstract | Links | BibTeX | Tags:
@inproceedings{tsiartas_context-driven_2009,
title = {Context-driven automatic bilingual movie subtitle alignment},
author = {Andreas Tsiartas and Prasanta Kumar Ghosh and Panayiotis G. Georgiou and Shrikanth Narayanan},
url = {http://ict.usc.edu/pubs/Context-driven%20automatic%20bilingual%20movie%20subtitle%20alignment.pdf},
year = {2009},
date = {2009-09-01},
booktitle = {Proceedings of Interspeech 2009},
address = {Brighton, UK},
abstract = {Movie subtitle alignment is a potentially useful approach for de- riving automatically parallel bilingual/multilingual spoken lan- guage data for automatic speech translation. In this paper, we consider the movie subtitle alignment task. We propose a dis- tance metric between utterances of different languages based on lexical features derived from bilingual dictionaries. We use the dynamic time warping algorithm to obtain the best alignment. The best F-score of ∼0.713 is obtained using the proposed ap- proach.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Mower, Emily; Mataric, Maja J.; Narayanan, Shrikanth
Evaluating Evaluators: A Case Study in Understanding the Benefits and Pitfalls of Multi-Evaluator Modeling Proceedings Article
In: Proceedings of Interspeech 2009, Brighton, UK, 2009.
Abstract | Links | BibTeX | Tags:
@inproceedings{mower_evaluating_2009,
title = {Evaluating Evaluators: A Case Study in Understanding the Benefits and Pitfalls of Multi-Evaluator Modeling},
author = {Emily Mower and Maja J. Mataric and Shrikanth Narayanan},
url = {http://ict.usc.edu/pubs/Evaluating%20Evaluators-%20A%20Case%20Study%20in%20Understanding%20the%20Benefits%20and%20Pitfalls%20of%20Multi-Evaluator%20Modeling.pdf},
year = {2009},
date = {2009-09-01},
booktitle = {Proceedings of Interspeech 2009},
address = {Brighton, UK},
abstract = {Emotion perception is a complex process, often measured using stimuli presentation experiments that query evaluators for their perceptual ratings of emotional cues. These evaluations contain large amounts of variability both related and unrelated to the evaluated utterances. One approach to handling this variability is to model emotion perception at the individual level. However, the perceptions of specific users may not adequately capture the emotional acoustic properties of an utterance. This problem can be mitigated by the common technique of averaging evalu- ations from multiple users. We demonstrate that this averaging procedure improves classification performance when compared to classification results from models created using individual- specific evaluations. We also demonstrate that the performance increases are related to the consistency with which evaluators label data. These results suggest that the acoustic properties of emotional speech are better captured using models formed from averaged evaluations rather than from individual-specific eval- uations.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Pütten, Astrid M.; Gratch, Jonathan; Kang, Sin-Hwa; Krämer, Nicole
It doesn't matter what you are! Comparing interacting with an autonomous virtual person with interacting with a virtually represented human Proceedings Article
In: Proceedings of the 6th Conference of the Media Psychology Division of the German Psychological Society, University of Duisberg-Essen, Germany, 2009.
Abstract | Links | BibTeX | Tags: Virtual Humans
@inproceedings{von_der_putten_it_2009,
title = {It doesn't matter what you are! Comparing interacting with an autonomous virtual person with interacting with a virtually represented human},
author = {Astrid M. Pütten and Jonathan Gratch and Sin-Hwa Kang and Nicole Krämer},
url = {http://ict.usc.edu/pubs/It%20doesnt%20matter%20what%20you%20are.pdf},
year = {2009},
date = {2009-09-01},
booktitle = {Proceedings of the 6th Conference of the Media Psychology Division of the German Psychological Society},
address = {University of Duisberg-Essen, Germany},
abstract = {According to the Threshold Model of Social Influence (Blascovich et al., 2002) the social influence of real persons will always be high, whereas the influence of an artificial entity depends on the realism of its behavior. Contrariwise, the Ethopeia concept (Nass & Moon, 2000) predicts that automatic social reactions are triggered by situations as soon as they include social cues. The presented study evaluates whether the participants' belief in interacting with either an avatar (a virtual representation of a human) or an agent (autonomous virtual person) lead to different social effects.},
keywords = {Virtual Humans},
pubstate = {published},
tppubtype = {inproceedings}
}
Lee, Jina; Marsella, Stacy C.
Learning Models of Speaker Head Nods with Affective Information Proceedings Article
In: The 3rd International Conference on Affective Computing and Intelligent Interaction (ACII 2009), Amsterdam, The Netherlands, 2009.
Abstract | Links | BibTeX | Tags: Social Simulation
@inproceedings{lee_learning_2009,
title = {Learning Models of Speaker Head Nods with Affective Information},
author = {Jina Lee and Stacy C. Marsella},
url = {http://ict.usc.edu/pubs/Learning%20Models%20of%20Speaker%20Head%20Nods%20with%20Affective%20Information.pdf},
year = {2009},
date = {2009-09-01},
booktitle = {The 3rd International Conference on Affective Computing and Intelligent Interaction (ACII 2009)},
address = {Amsterdam, The Netherlands},
abstract = {During face-to-face conversation, the speaker's head is continually in motion. These movements serve a variety of important communicative functions, and may also be influ- enced by our emotions. The goal for this work is to build a domain-independent model of speaker's head movements and investigate the effect of using affective information dur- ing the learning process. Once the model is learned, it can later be used to generate head movements for virtual agents. In this paper, we describe our machine-learning approach to predict speaker's head nods using an annotated corpora of face-to-face human interaction and emotion labels gener- ated by an affect recognition model. We describe the feature selection process, training process, and the comparison of results of the learned models under varying conditions. The results show that using affective information can help pre- dict head nods better than when no affective information is used.},
keywords = {Social Simulation},
pubstate = {published},
tppubtype = {inproceedings}
}
Melo, Celso M.; Zheng, Liang; Gratch, Jonathan
Expression of Moral Emotions in Cooperating Agents Proceedings Article
In: Proceedings of the 9th International Conference on Intelligent Virtual Agents (IVA), Amsterdam, The Netherlands, 2009.
Abstract | Links | BibTeX | Tags: Virtual Humans
@inproceedings{de_melo_expression_2009-1,
title = {Expression of Moral Emotions in Cooperating Agents},
author = {Celso M. Melo and Liang Zheng and Jonathan Gratch},
url = {http://ict.usc.edu/pubs/Expression%20of%20Moral%20Emotions%20in%20Cooperating%20Agents.pdf},
year = {2009},
date = {2009-09-01},
booktitle = {Proceedings of the 9th International Conference on Intelligent Virtual Agents (IVA)},
address = {Amsterdam, The Netherlands},
abstract = {Moral emotions have been argued to play a central role in the emergence of cooperation in human-human interactions. This work describes an experiment which tests whether this insight carries to virtual human-human interactions. In particular, the paper describes a repeated-measures experiment where subjects play the iterated prisoner's dilemma with two versions of the virtual human: (a) neutral, which is the control condition; (b) moral, which is identical to the control condition except that the virtual human expresses gratitude, distress, remorse, reproach and anger through the face according to the action history of the game. Our results indicate that subjects cooperate more with the virtual human in the moral condition and that they perceive it to be more human-like. We discuss the relevance these results have for building agents which are successful in cooperating with humans.},
keywords = {Virtual Humans},
pubstate = {published},
tppubtype = {inproceedings}
}
Melo, Celso M.; Gratch, Jonathan
The Effect of Color on Expression of Joy and Sadness in Virtual Humans Proceedings Article
In: Proceedings of the 9th International Conference on Intelligent Virtual Agents (IVA), Amsterdam, The Netherlands, 2009.
Abstract | Links | BibTeX | Tags: Virtual Humans
@inproceedings{de_melo_effect_2009,
title = {The Effect of Color on Expression of Joy and Sadness in Virtual Humans},
author = {Celso M. Melo and Jonathan Gratch},
url = {http://ict.usc.edu/pubs/The%20Effect%20of%20Color%20on%20Expression%20of%20Joy%20and%20Sadness%20in%20Virtual%20Humans.pdf},
year = {2009},
date = {2009-09-01},
booktitle = {Proceedings of the 9th International Conference on Intelligent Virtual Agents (IVA)},
address = {Amsterdam, The Netherlands},
abstract = {For centuries artists have been exploring color to express emotions. Following this insight, the paper describes an approach to learn how to use color to influence the perception of emotions in virtual humans. First, a model of lighting and filters inspired on the visual arts is integrated with a virtual human platform to manipulate color. Next, an evolutionary model, based on genetic algorithms, is created to evolve mappings between emotions and lighting and filter parameters. A first study is, then, conducted where subjects evolve mappings for joy and sadness without being aware of the evolutionary model. In a second study, the features which characterize the mappings are analyzed. Results show that virtual human images of joy tend to be brighter, more saturated and have more colors than images of sadness. The paper discusses the relevance of the results for the fields of expression of emotions and virtual humans.},
keywords = {Virtual Humans},
pubstate = {published},
tppubtype = {inproceedings}
}
Kim, Jangwon; Lee, Sungbok; Narayanan, Shrikanth
A Detailed Study of Word-Position Effects on Emotion Expression in Speech Proceedings Article
In: Proceedings of Interspeech 2009, Brighton UK, 2009.
Abstract | Links | BibTeX | Tags:
@inproceedings{kim_detailed_2009,
title = {A Detailed Study of Word-Position Effects on Emotion Expression in Speech},
author = {Jangwon Kim and Sungbok Lee and Shrikanth Narayanan},
url = {http://ict.usc.edu/pubs/A%20Detailed%20Study%20of%20Word-Position%20Effects%20on%20Emotion%20Expression%20in%20Speech.pdf},
year = {2009},
date = {2009-09-01},
booktitle = {Proceedings of Interspeech 2009},
address = {Brighton UK},
abstract = {We investigate emotional effects on articulatory-acoustic speech characteristics with respect to word location within a sentence. We examined the hypothesis that emotional effect will vary based on word position by first examining articulatory features manually extracted from Electromagnetic articulography data. Initial articulatory data analyses indicated that the emotional effects on sentence medial words are significantly stronger than on initial words. To verify that observation further, we expanded our hypothesis testing to include both acoustic and articulatory data, and a consideration of an expanded set of words from different locations. Results suggest that emotional effects are generally more significant on sentence medial words than sentence initial and final words. This finding suggests that word location needs to be considered as a factor in emotional speech processing.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Wang, Ning; Gratch, Jonathan
Rapport and Facial Expression Proceedings Article
In: 3rd International Conference on Affective Computing and Intelligent Interaction (ACII 2009), Amsterdam, The Netherlands, 2009.
Abstract | Links | BibTeX | Tags: Virtual Humans
@inproceedings{wang_rapport_2009,
title = {Rapport and Facial Expression},
author = {Ning Wang and Jonathan Gratch},
url = {http://ict.usc.edu/pubs/Rapport%20and%20Facial%20Expression.pdf},
year = {2009},
date = {2009-09-01},
booktitle = {3rd International Conference on Affective Computing and Intelligent Interaction (ACII 2009)},
address = {Amsterdam, The Netherlands},
abstract = {How to build virtual agents that establish rapport with human? According to Tickle-Degnen and Rosenthal [4], the three essential components of rapport are mutual attentiveness, positivity and coordination. In our previous work, we designed an embodied virtual agent to establish rapport with a human speaker by providing rapid and contingent nonverbal feedback [13] [22]. How do we know that a human speaker is feeling a sense of rapport? In this paper, we focus on the positivity component of rapport by investigating the relationship of human speakers' facial expressions on the establishment of rapport. We used an automatic facial expression coding tool called CERT to analyze the human dyad interactions and human-virtual human interactions. Results show that recognizing positive facial displays alone may be insufficient and that recognized negative facial displays was more diagnostic in assessing the level of rapport between participants.},
keywords = {Virtual Humans},
pubstate = {published},
tppubtype = {inproceedings}
}
Paksima, Taghi; Georgila, Kallirroi; Moore, Johanna D.
Evaluating the Effectiveness of Information Presentation in a Full End-To-End Dialogue System Proceedings Article
In: 10th SIGdial Workshop on Discourse and Dialogue, pp. 1–10, Association for Computational Linguistics, London, UK, 2009.
Abstract | Links | BibTeX | Tags:
@inproceedings{paksima_evaluating_2009,
title = {Evaluating the Effectiveness of Information Presentation in a Full End-To-End Dialogue System},
author = {Taghi Paksima and Kallirroi Georgila and Johanna D. Moore},
url = {http://ict.usc.edu/pubs/Evaluating%20the%20Effectiveness%20of%20Information%20Presentation%20in%20a%20Full%20End-To-End%20Dialogue%20System.pdf},
year = {2009},
date = {2009-09-01},
booktitle = {10th SIGdial Workshop on Discourse and Dialogue},
pages = {1–10},
publisher = {Association for Computational Linguistics},
address = {London, UK},
abstract = {Recent work on information presenta- tion in dialogue systems combines user modelling (UM) and stepwise refine- ment through clustering and summarisa- tion (SR) in the UMSR approach. An eval- uation in which participants rated dialogue transcripts showed that UMSR presents complex trade-offs understandably, pro- vides users with a good overview of their options, and increases users' confidence that all relevant options have been pre- sented (Demberg and Moore, 2006). In this paper, we evaluate the effectiveness of the UMSR approach in a more realis- tic setting, by incorporating this informa- tion presentation technique into a full end- to-end dialogue system in the city infor- mation domain, and comparing it with the traditional approach of presenting infor- mation sequentially. Our results suggest that despite complications associated with a real dialogue system setting, the UMSR model retains its advantages.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Marsella, Stacy C.; Lee, Jina
Predicting Speaker Head Nods and the Effects of Affective Information Proceedings Article
In: 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops, 2009.
Abstract | Links | BibTeX | Tags: Social Simulation
@inproceedings{marsella_predicting_2009,
title = {Predicting Speaker Head Nods and the Effects of Affective Information},
author = {Stacy C. Marsella and Jina Lee},
url = {http://ict.usc.edu/pubs/Predicting%20Speaker%20Head%20Nods%20and%20the%20Effects%20of%20Affective%20Information.pdf},
year = {2009},
date = {2009-09-01},
booktitle = {3rd International Conference on Affective Computing and Intelligent Interaction and Workshops},
volume = {12},
abstract = {During face-to-face conversation, our body is continually in motion with various head, gesture, and posture movements. Based on findings of the communicative functions served by these nonverbal behaviors, many virtual agent systems have modeled them to make the virtual agent look more effective and believable. One channel of nonverbal behaviors that has received less attention is head movements, despite the important functions served by them. The goal for this work is to build a domain-independent model of speaker's head movements that could be used to generate head movements for virtual agents. In this paper, we present a machine learning approach for learning models of head movements by focusing on when speaker head nods should occur and conduct evaluation studies that compare the nods generated by this work to our previous approach of using hand-crafted rules},
keywords = {Social Simulation},
pubstate = {published},
tppubtype = {inproceedings}
}
Han, Kyu J.; Narayanan, Shrikanth
Improved Speaker Diarization of Meeting Speech with Recurrent Selection of Representative Speech Segments and Participant Interaction Pattern Modeling Proceedings Article
In: Proceedings of Interspeech 2009, Brighton, UK, 2009.
Abstract | Links | BibTeX | Tags:
@inproceedings{han_improved_2009,
title = {Improved Speaker Diarization of Meeting Speech with Recurrent Selection of Representative Speech Segments and Participant Interaction Pattern Modeling},
author = {Kyu J. Han and Shrikanth Narayanan},
url = {http://ict.usc.edu/pubs/Improved%20Speaker%20Diarization.pdf},
year = {2009},
date = {2009-09-01},
booktitle = {Proceedings of Interspeech 2009},
address = {Brighton, UK},
abstract = {In this work we describe two distinct novel improvements to our speaker diarization system, previously proposed for anal- ysis of meeting speech. The first approach focuses on recurrent selection of representative speech segments for speaker clus- tering while the other is based on participant interaction pat- tern modeling. The former selects speech segments with high relevance to speaker clustering, especially from a robust clus- ter modeling perspective, and keeps updating them throughout clustering procedures. The latter statistically models conver- sation patterns between meeting participants and applies it as a priori information when refining diarization results. Experi- mental results reveal that the two proposed approaches provide performance enhancement by 29.82% (relative) in terms of di- arization error rate in tests on 13 meeting excerpts from various meeting speech corpora.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Kang, Sin-Hwa; Gratch, Jonathan
Interactants' Most Intimate Self-Disclosure in Interactions with Virtual Humans Proceedings Article
In: 9th International Conference on Intelligent Virtual Agents, Amsterdam, The Netherlands, 2009.
Abstract | Links | BibTeX | Tags: Virtual Humans
@inproceedings{kang_interactants_2009,
title = {Interactants' Most Intimate Self-Disclosure in Interactions with Virtual Humans},
author = {Sin-Hwa Kang and Jonathan Gratch},
url = {http://ict.usc.edu/pubs/Interactants%E2%80%99%20Most%20Intimate%20Self-Disclosure%20in%20Interactions%20with%20Virtual%20Humans.pdf},
year = {2009},
date = {2009-09-01},
booktitle = {9th International Conference on Intelligent Virtual Agents},
address = {Amsterdam, The Netherlands},
abstract = {This study explored the effect of the combination of visual fidelity of a virtual human and interactants' anticipated future interaction on self-disclosure in emotionally engaged and synchronous communication. The preliminary results were compared between interactions with embodied virtual agents and with real humans. We par-ticularly aimed at investigating ways to allow interactants' intimate self-disclosure while securing their anonymity, even with minimal cues of an embodied virtual agent, when interactants anticipate their future interaction with interaction partners. The results of preliminary data analysis showed that interactants revealed intimate information about their most common sexual fantasy when they had anticipated future interaction with their interaction partners.},
keywords = {Virtual Humans},
pubstate = {published},
tppubtype = {inproceedings}
}
Chance, Eric; Morie, Jacquelyn
Method for Custom Facial Animation and Lip-Sync in an Unsupported Environment, Second Life Proceedings Article
In: Lecture Notes in Computer Science; Proceedings of the 9th International Workshop on Intelligent Virtual Agents (IVA), Amsterdam, The Netherlands, 2009.
Abstract | Links | BibTeX | Tags:
@inproceedings{chance_method_2009,
title = {Method for Custom Facial Animation and Lip-Sync in an Unsupported Environment, Second Life},
author = {Eric Chance and Jacquelyn Morie},
url = {http://ict.usc.edu/pubs/Method%20for%20Custom%20Facial%20Animation%20and%20Lip-Sync%20in%20an%20Unsupported%20Environment,%20Second%20Life.pdf},
year = {2009},
date = {2009-09-01},
booktitle = {Lecture Notes in Computer Science; Proceedings of the 9th International Workshop on Intelligent Virtual Agents (IVA)},
volume = {5773},
address = {Amsterdam, The Netherlands},
abstract = {The virtual world of Second Lifeâ„¢ does not offer support for complex facial animations, such as those needed for an intelligent virtual agent to lip sync to audio clips. However, it is possible to access a limited range of default facial animations through the native scripting language, LSL. Our solution to produce lip sync in this environment is to rapidly trigger and stop these default animations in custom sequences to produce the illusion that the intelligent virtual agent is speaking the phrases being heard.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Marsella, Stacy C.; Gratch, Jonathan; Wang, Ning
Assessing the validity of a computational model of emotional coping Proceedings Article
In: International Conference on Affective Computing and Intelligent Interaction, Amsterdam, The Netherlands, 2009.
Abstract | Links | BibTeX | Tags: Social Simulation, Virtual Humans
@inproceedings{marsella_assessing_2009,
title = {Assessing the validity of a computational model of emotional coping},
author = {Stacy C. Marsella and Jonathan Gratch and Ning Wang},
url = {http://ict.usc.edu/pubs/Assessing%20the%20validity%20of%20a%20computational%20model%20of%20emotional%20coping.pdf},
year = {2009},
date = {2009-09-01},
booktitle = {International Conference on Affective Computing and Intelligent Interaction},
address = {Amsterdam, The Netherlands},
abstract = {In this paper we describe the results of a rigorous empirical study evaluating the coping responses of a computational model of emotion. We discuss three key kinds of coping, Wishful Thinking, Resignation and Dis-tancing that impact an agent's beliefs, intentions and desires, and compare these coping responses to related work in the attitude change literature. We discuss the EMA computational model of emotion and identify sev-eral hypotheses it makes concerning these coping processes. We assess these hypotheses against the beha-vior of human subjects playing a competitive board game, using monetary gains and losses to induce emo-tion and coping. Subject's appraisals, emotional state and coping responses were indexed at key points throughout a game, revealing a pattern of subject's al-tering their beliefs, desires and intentions as the game unfolds. The results clearly support several of the hypo-theses on coping responses but also identify (a) exten-sions to how EMA models Wishful Thinking as well as (b) individual differences in subject's coping responses.},
keywords = {Social Simulation, Virtual Humans},
pubstate = {published},
tppubtype = {inproceedings}
}
Jones, Andrew; Lang, Magnus; Fyffe, Graham; Yu, Xueming; Busch, Jay; McDowall, Ian; Bolas, Mark; Debevec, Paul
Achieving Eye Contact in a One-to-Many 3D Video Teleconferencing System Journal Article
In: ACM Transactions on Graphics (TOG) - Proceedings of ACM SIGGRAPH 2009, vol. 28, no. 3, 2009.
Abstract | Links | BibTeX | Tags: Graphics, MxR
@article{jones_achieving_2009,
title = {Achieving Eye Contact in a One-to-Many 3D Video Teleconferencing System},
author = {Andrew Jones and Magnus Lang and Graham Fyffe and Xueming Yu and Jay Busch and Ian McDowall and Mark Bolas and Paul Debevec},
url = {http://ict.usc.edu/pubs/Achieving%20Eye%20Contact%20in%20a%20One-to-Many%203D%20Video%20Teleconferencing%20System.pdf},
year = {2009},
date = {2009-08-01},
journal = {ACM Transactions on Graphics (TOG) - Proceedings of ACM SIGGRAPH 2009},
volume = {28},
number = {3},
abstract = {We present a set of algorithms and an associated display system capable of producing correctly rendered eye contact between a three-dimensionally transmitted remote participant and a group of observers in a 3D teleconferencing system. The participant's face is scanned in 3D at 30Hz and transmitted in real time to an autostereo- scopic horizontal-parallax 3D display, displaying him or her over more than a 180â—¦ field of view observable to multiple observers. To render the geometry with correct perspective, we create a fast vertex shader based on a 6D lookup table for projecting 3D scene vertices to a range of subject angles, heights, and distances. We generalize the projection mathematics to arbitrarily shaped display surfaces, which allows us to employ a curved concave display surface to focus the high speed imagery to individual observers. To achieve two-way eye contact, we capture 2D video from a cross-polarized camera reflected to the position of the virtual participant's eyes, and display this 2D video feed on a large screen in front of the real par- ticipant, replicating the viewpoint of their virtual self. To achieve correct vertical perspective, we further leverage this image to track the position of each audience member's eyes, allowing the 3D dis- play to render correct vertical perspective for each of the viewers around the device. The result is a one-to-many 3D teleconferenc- ing system able to reproduce the effects of gaze, attention, and eye contact generally missing in traditional teleconferencing systems.},
keywords = {Graphics, MxR},
pubstate = {published},
tppubtype = {article}
}
Wilson, Cyrus A.; Ghosh, Abhijeet; Peers, Pieter; Chiang, Jen-Yuan; Busch, Jay; Debevec, Paul
2D and 3D facial correspondences via photometric alignment Proceedings Article
In: SIGGRAPH, New Orleans, LA, 2009, ISBN: 978-1-60558-834-6.
Abstract | Links | BibTeX | Tags: Graphics
@inproceedings{wilson_2d_2009,
title = {2D and 3D facial correspondences via photometric alignment},
author = {Cyrus A. Wilson and Abhijeet Ghosh and Pieter Peers and Jen-Yuan Chiang and Jay Busch and Paul Debevec},
url = {http://ict.usc.edu/pubs/2D%20and%203D%20facial%20correspondences%20via%20photometric%20alignment.pdf},
doi = {10.1145/1597990.1598018},
isbn = {978-1-60558-834-6},
year = {2009},
date = {2009-08-01},
booktitle = {SIGGRAPH},
address = {New Orleans, LA},
abstract = {Capturing facial geometry that is high-resolution, yet easy to animate, remains a difficult challenge. While a single scanned geometry may be straightforward to animate smoothly, it may not always yield realistic fine scale detail when deformed into different facial expressions. Combining scans of multiple facial expressions, however, is only practical if geometrical correspondences between the different scanned expressions are available. Correspondences obtained based on locations of facial landmarks or of placed markers are often sparse, especially compared to fine-scale structures such as individual skin pores. The resulting misalignment of fine detail can introduce artifacts or blur out details we wish to preserve.},
keywords = {Graphics},
pubstate = {published},
tppubtype = {inproceedings}
}
Parsons, Thomas D.; Rizzo, Albert; Rogers, Steven A.; York, Philip
Virtual Reality in Paediatric Rehabilitation: A Review Journal Article
In: Developmental Neurorehabilitation, vol. 12, no. 4, pp. 224–238, 2009.
Abstract | Links | BibTeX | Tags: MedVR
@article{parsons_virtual_2009-1,
title = {Virtual Reality in Paediatric Rehabilitation: A Review},
author = {Thomas D. Parsons and Albert Rizzo and Steven A. Rogers and Philip York},
url = {http://ict.usc.edu/pubs/Virtual%20reality%20in%20paediatric%20rehabilitation-%20A%20review.pdf},
doi = {10.1080/17518420902991719},
year = {2009},
date = {2009-08-01},
journal = {Developmental Neurorehabilitation},
volume = {12},
number = {4},
pages = {224–238},
abstract = {Objective: To provide a narrative review of studies regarding the outcomes of Virtual Reality (VR)-based treatment and rehabilitation programmes within the paediatric population. Methods: Studies related to the use of VR across a number of paediatric areas (e.g. cerebral palsy, autism, foetal alcohol syndrome and attention deficits) were identified and summarized. Results: Outcomes from the studies reviewed provide preliminary support for the use of VR. Conclusion: VR may be an effective treatment method for specific disorders, although the generalizability of this literature is hindered by several methodological limitations, such as small samples and the absence of appropriate control participants.},
keywords = {MedVR},
pubstate = {published},
tppubtype = {article}
}
Weyrich, Tim; Peers, Pieter; Matusik, Wojciech; Rusinkiewicz, Szymon
Fabricating Microgeometry for Custom Surface Reflectance Journal Article
In: ACM Transactions on Graphics, vol. 28, no. 3, 2009.
Abstract | Links | BibTeX | Tags:
@article{weyrich_fabricating_2009,
title = {Fabricating Microgeometry for Custom Surface Reflectance},
author = {Tim Weyrich and Pieter Peers and Wojciech Matusik and Szymon Rusinkiewicz},
url = {http://ict.usc.edu/pubs/Fabricating%20Microgeometry%20for%20Custom%20Surface%20Reflectance.pdf},
year = {2009},
date = {2009-08-01},
journal = {ACM Transactions on Graphics},
volume = {28},
number = {3},
abstract = {We propose a system for manufacturing physical surfaces that, in aggregate, exhibit a desired surface appearance. Our system begins with a user specification of a BRDF, or simply a highlight shape, and infers the required distribution of surface slopes. We sample this distribution, optimize for a maximally-continuous and valley-minimizing height field, and finally mill the surface using a computer-controlled machine tool. We demonstrate a variety of surfaces, ranging from reproductions of measured BRDFs to materials with unconventional highlights.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Song, Ying; Tong, Xin; Pellacini, Fabio; Peers, Pieter
SubEdit: A Representation for Editing Measured Heterogeneous Subsurface Scattering Journal Article
In: ACM Transactions on Graphics, vol. 28, no. 3, 2009.
Abstract | Links | BibTeX | Tags:
@article{song_subedit_2009,
title = {SubEdit: A Representation for Editing Measured Heterogeneous Subsurface Scattering},
author = {Ying Song and Xin Tong and Fabio Pellacini and Pieter Peers},
url = {http://ict.usc.edu/pubs/SubEdit-%20A%20Representation%20for%20Editing%20Measured%20Heterogeneous%20Subsurface%20Scattering.pdf},
year = {2009},
date = {2009-08-01},
journal = {ACM Transactions on Graphics},
volume = {28},
number = {3},
abstract = {In this paper we present SubEdit, a representation for editing the BSSRDF of heterogeneous subsurface scattering acquired from real-world samples. Directly editing measured raw data is difficult due to the non-local impact of heterogeneous subsurface scattering on the appearance. Our SubEdit representation decouples these non-local effects into the product of two local scattering profiles defined at respectively the incident and outgoing surface locations. This allows users to directly manipulate the appearance of single surface locations and to robustly make selections. To further facilitate editing, we reparameterize the scattering profiles into the local appearance concepts of albedo, scattering range, and profile shape. Our method preserves the visual quality of the measured material after editing by maintaining the consistency of subsurface transport for all edits. SubEdit fits measured data well while remaining efficient enough to support interactive rendering and manipulation. We illustrate the suitability of SubEdit as a representation for editing by applying various complex modifications on a wide variety of measured heterogeneous subsurface scattering materials.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Vipperla, Ravichander; Wolters, Maria; Georgila, Kallirroi; Renals, Steve
Speech Input from Older Users in Smart Environments: Challenges and perspectives Proceedings Article
In: Proceedings of Human-Computer Interaction Intelligent and Ubiquitous Interaction Environments, 2009.
Abstract | Links | BibTeX | Tags:
@inproceedings{vipperla_speech_2009,
title = {Speech Input from Older Users in Smart Environments: Challenges and perspectives},
author = {Ravichander Vipperla and Maria Wolters and Kallirroi Georgila and Steve Renals},
url = {http://ict.usc.edu/pubs/Speech%20Input%20from%20Older%20Users%20in%20Smart%20Environments.pdf},
year = {2009},
date = {2009-07-01},
booktitle = {Proceedings of Human-Computer Interaction Intelligent and Ubiquitous Interaction Environments},
abstract = {Although older people are an important user group for smart envi- ronments, there has been relatively little work on adapting natural language in- terfaces to their requirements. In this paper, we focus on a particularly thorny problem: processing speech input from older users. Our experiments on the MATCH corpus show clearly that we need age-specific adaptation in order to recognize older users' speech reliably. Language models need to cover typical interaction patterns of older people, and acoustic models need to accommodate older voices. Further research is needed into intelligent adaptation techniques that will allow existing large, robust systems to be adapted with relatively small amounts of in-domain, age appropriate data. In addition, older users need to be supported with adequate strategies for handling speech recognition errors.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Hays, Matthew; Lane, H. Chad; Auerbach, Daniel; Core, Mark; Gomboc, Dave; Rosenberg, Milton
Feedback Specificity and the Learning of Intercultural Communication Skills Proceedings Article
In: International Conference on Artificial Intelligence in Education, Brighton, UK, 2009.
Abstract | Links | BibTeX | Tags:
@inproceedings{hays_feedback_2009,
title = {Feedback Specificity and the Learning of Intercultural Communication Skills},
author = {Matthew Hays and H. Chad Lane and Daniel Auerbach and Mark Core and Dave Gomboc and Milton Rosenberg},
url = {http://ict.usc.edu/pubs/Feedback%20Specificity%20and%20the%20Learning%20of%20Intercultural%20Communication%20Skills.pdf},
year = {2009},
date = {2009-07-01},
booktitle = {International Conference on Artificial Intelligence in Education},
address = {Brighton, UK},
abstract = {The role of explicit feedback in learning has been studied from a variety of perspectives and in many contexts. In this paper, we examine the impact of the specificity of feedback delivered by an intelligent tutoring system in a game-based environment for cultural learning. We compared two versions: one that provided only "bottom-out" hints and feedback versus one that provided only conceptual messages. We measured during-training performance, in-game transfer, and long- term retention. Consistent with our hypotheses, specific feedback utterances produced inferior learning on the in-game transfer task when compared to conceptual utterances. No differences were found on a web-based post-test. We discuss possible explanations for these findings, particularly as they relate to the learning of loosely defined skills and serious games.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Traum, David
Models of Culture for Virtual Human Conversation Proceedings Article
In: Human Computer Interaction International (HCII), pp. 434–440, San Diego, CA, 2009.
Abstract | Links | BibTeX | Tags: Virtual Humans
@inproceedings{traum_models_2009,
title = {Models of Culture for Virtual Human Conversation},
author = {David Traum},
url = {http://ict.usc.edu/pubs/Models%20of%20Culture%20for%20Virtual%20Human%20Conversation.pdf},
year = {2009},
date = {2009-07-01},
booktitle = {Human Computer Interaction International (HCII)},
pages = {434–440},
address = {San Diego, CA},
abstract = {In this paper, we survey different types of Models of culture for virtual humans. Virtual humans are artificial agents that include both a visual human-like body and intelligent cognition driving action of the body. Culture covers a wide range of common knowledge of behavior and communication that can be used in a number of ways including interpreting the meaning of ac- tion, establishing identity, expressing meaning, and inference about the per- former. We look at several examples of existing cultural models and point out remaining steps for a more full model of culture.},
keywords = {Virtual Humans},
pubstate = {published},
tppubtype = {inproceedings}
}
Morency, Louis-Philippe; Whitehill, Jacob; Movellan, Javier
Monocular Head Pose Estimation using Generalized Adaptive View-based Appearance Model Journal Article
In: Image and Vision Computing, 2009.
Abstract | Links | BibTeX | Tags:
@article{morency_monocular_2009,
title = {Monocular Head Pose Estimation using Generalized Adaptive View-based Appearance Model},
author = {Louis-Philippe Morency and Jacob Whitehill and Javier Movellan},
url = {http://ict.usc.edu/pubs/Monocular%20Head%20Pose%20Estimation%20using%20Generalized%20Adaptive%20View-based%20Appearance%20Model.pdf},
year = {2009},
date = {2009-07-01},
journal = {Image and Vision Computing},
abstract = {Accurately estimating the person's head position and orientation is an important task for a wide range of applications such as driver awareness, meeting analysis and human-robot interaction. Over the past two decades, many approaches have been suggested to solve this problem, each with its own advantages and disad- vantages. In this paper, we present a probabilistic framework called Generalized Adaptive View-based Appearance Model (GAVAM) which integrates the advan- tages from three of these approaches: (1) the automatic initialization and stability of static head pose estimation, (2) the relative precision and user-independence of differential registration, and (3) the robustness and bounded drift of keyframe tracking. In our experiments, we show how the GAVAM model can be used to estimate head position and orientation in real-time using a simple monocular cam- era. Our experiments on two previously published datasets show that the GAVAM framework can accurately track for a long period of time with an average accu- racy of 3.5â—¦ and 0.75in when compared with an inertial sensor and a 3D magnetic sensor.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Rosenbloom, Paul
Towards a New Cognitive Hourglass: Uniform Implementation of Cognitive Architecture via Factor Graphs Proceedings Article
In: Proceedings of the 9th International Conference on Cognitive Modeling (ICCM 2009), Manchester, UK, 2009.
Abstract | Links | BibTeX | Tags: CogArch, Cognitive Architecture, Virtual Humans
@inproceedings{rosenbloom_towards_2009,
title = {Towards a New Cognitive Hourglass: Uniform Implementation of Cognitive Architecture via Factor Graphs},
author = {Paul Rosenbloom},
url = {http://ict.usc.edu/pubs/Towards%20a%20New%20Cognitive%20Hourglass.pdf},
year = {2009},
date = {2009-07-01},
booktitle = {Proceedings of the 9th International Conference on Cognitive Modeling (ICCM 2009)},
address = {Manchester, UK},
abstract = {As cognitive architectures become ever more ambitious in the range of phenomena they are to assist in producing and modeling, there is increasing pressure for diversity in the mechanisms they embody. Yet uniformity remains critical for both elegance and extensibility. Here, the search for uniformity is continued, but shifted downwards in the cognitive hierarchy to the implementation level. Factor graphs are explored as a promising core, with initial steps towards a reimplementation of Soar. The ultimate aim is a uniform implementation level for cognitive architectures affording both heightened elegance and expanded coverage.},
keywords = {CogArch, Cognitive Architecture, Virtual Humans},
pubstate = {published},
tppubtype = {inproceedings}
}
Wang, Ning; Gratch, Jonathan
Can Virtual Human Build Rapport and Promote Learning? Proceedings Article
In: Annual Conference on Artificial Intelligence in Education, Brighton UK, 2009.
Abstract | Links | BibTeX | Tags: Virtual Humans
@inproceedings{wang_can_2009,
title = {Can Virtual Human Build Rapport and Promote Learning?},
author = {Ning Wang and Jonathan Gratch},
url = {http://ict.usc.edu/pubs/Can%20Virtual%20Human%20Build%20Rapport%20and%20Promote%20Learning.pdf},
year = {2009},
date = {2009-07-01},
booktitle = {Annual Conference on Artificial Intelligence in Education},
address = {Brighton UK},
abstract = {Research show that teacher’s nonverbal immediacy can have a positive impact on student’s cognitive learning and affect [31]. This paper investigates the effectiveness of nonverbal immediacy using a virtual human. The virtual human attempts to use immediacy feedback to create rapport with the learner. Results show that the virtual human established rapport with learners but did not help them achieve better learning results. The results also suggest that creating rapport is related to higher self-efficacy, and self-efficacy is related to better learning results.},
keywords = {Virtual Humans},
pubstate = {published},
tppubtype = {inproceedings}
}
Lane, H. Chad; Core, Mark; Forbell, Eric; Wray, Robert; Stensrud, Brian; Hamel, Laura
Pedagogical Experience Manipulation for Cultural Learning Proceedings Article
In: Proceedings of the Workshop on Culturally Aware Tutoring Systems, 14th International Conference on AI in Education, 2009.
Abstract | Links | BibTeX | Tags:
@inproceedings{lane_pedagogical_2009,
title = {Pedagogical Experience Manipulation for Cultural Learning},
author = {H. Chad Lane and Mark Core and Eric Forbell and Robert Wray and Brian Stensrud and Laura Hamel},
url = {http://ict.usc.edu/pubs/Pedagogical%20Experience%20Manipulation%20for%20Cultural%20Learning.pdf},
year = {2009},
date = {2009-07-01},
booktitle = {Proceedings of the Workshop on Culturally Aware Tutoring Systems, 14th International Conference on AI in Education},
abstract = {Acquiring intercultural competence is challenging. Although intelligent learning environments developed to enhance cultural learning can be effective, there is limited evidence regarding how best to dynamically manipulate these environments in support of learning. Further, the space of potential manipulations is extremely large and sometimes tangled with the implementation details of particular learning systems in particular domains. This paper offers a framework for organizing approaches to such dynamic tailoring of the learning experience. The framework is hypothesized to be useful as a general tool for the community to organize and present alternative approaches to tailoring. To highlight the use of the framework, we examine one potential tailoring option in detail in the context of an existing simulation for learning intercultural competence.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
McAlinden, Ryan; Gordon, Andrew S.; Lane, H. Chad; Pynadath, David V.
UrbanSim: A Game-based Simulation for Counterinsurgency and Stability-focused Operations Proceedings Article
In: Workshop on Intelligent Educational Games, 14th International Conference on Artificial Intelligence in Education, Brighton, UK, 2009.
Abstract | Links | BibTeX | Tags: Learning Sciences, Social Simulation, The Narrative Group
@inproceedings{mcalinden_urbansim_2009,
title = {UrbanSim: A Game-based Simulation for Counterinsurgency and Stability-focused Operations},
author = {Ryan McAlinden and Andrew S. Gordon and H. Chad Lane and David V. Pynadath},
url = {http://ict.usc.edu/pubs/UrbanSim-%20A%20Game-based%20Simulation%20for%20Counterinsurgency%20and%20Stability-focused%20Operations.pdf},
year = {2009},
date = {2009-07-01},
booktitle = {Workshop on Intelligent Educational Games, 14th International Conference on Artificial Intelligence in Education},
address = {Brighton, UK},
abstract = {The UrbanSim Learning Package is a simulation-based training application designed for the U.S. Army to develop commanders' skills for conducting counterinsurgency operations. UrbanSim incorporates multiple artificial intelligence (AI) technologies in order to provide an effective training experience, three of which are described in this paper. First, UrbanSim simulates the mental attitudes and actions of groups and individuals in an urban environment using the PsychSim reasoning engine. Second, UrbanSim interjects narrative elements into the training experience using a case-based story engine, driven by non-fiction stories told by experienced commanders. Third, UrbanSim provides intelligent tutoring using a simulation-based method for eliciting and evaluating learner decisions. UrbanSim represents a confluence of AI techniques that seek to bridge the gap between basic research and deployed AI systems.},
keywords = {Learning Sciences, Social Simulation, The Narrative Group},
pubstate = {published},
tppubtype = {inproceedings}
}
Gandhe, Sudeep; Whitman, Nicolle; Traum, David; Artstein, Ron
An Integrated Authoring Tool for Tactical Questioning Dialogue Systems Proceedings Article
In: Workshop on Knowledge and Reasoning in Practical Dialogue Systems, Pasadena, CA, 2009.
Abstract | Links | BibTeX | Tags: Virtual Humans
@inproceedings{gandhe_integrated_2009,
title = {An Integrated Authoring Tool for Tactical Questioning Dialogue Systems},
author = {Sudeep Gandhe and Nicolle Whitman and David Traum and Ron Artstein},
url = {http://ict.usc.edu/pubs/An%20Integrated%20Authoring%20Tool%20for%20Tactical%20Questioning%20Dialogue%20Systems.pdf},
year = {2009},
date = {2009-07-01},
booktitle = {Workshop on Knowledge and Reasoning in Practical Dialogue Systems},
address = {Pasadena, CA},
abstract = {We present an integrated authoring tool for rapid prototyping of dialogue systems for virtual humans taking part in tactical questioning simulations. The tool helps domain experts, who may have little or no knowledge of linguistics or computer science, to build virtual characters that can play the role of the interviewee. Working in a top-down fashion, the authoring process begins with specifying a domain of knowledge for the character; the authoring tool generates all relevant dialogue acts and allows authors to assign the language that will be used to refer to the domain elements. The authoring tool can also be used to manipulate some aspects of the dialogue strategies employed by the virtual characters, and it also supports re-using some of the authored content across different characters.},
keywords = {Virtual Humans},
pubstate = {published},
tppubtype = {inproceedings}
}
Georgila, Kallirroi
Using Integer Linear Programming for Detecting Speech Disfluencies Proceedings Article
In: Proceedings of the NAACL HLT 2009: Short Papers, pp. 109–112, Boulder, CO, 2009.
Abstract | Links | BibTeX | Tags:
@inproceedings{georgila_using_2009,
title = {Using Integer Linear Programming for Detecting Speech Disfluencies},
author = {Kallirroi Georgila},
url = {http://ict.usc.edu/pubs/Using%20Integer%20Linear%20Programming%20for%20Detecting%20Speech%20Disfluencies.pdf},
year = {2009},
date = {2009-06-01},
booktitle = {Proceedings of the NAACL HLT 2009: Short Papers},
pages = {109–112},
address = {Boulder, CO},
abstract = {We present a novel two-stage technique for detecting speech disfluencies based on Integer Linear Programming (ILP). In the first stage we use state-of-the-art models for speech disfluency detection, in particular, hidden-event language models, maximum entropy models and conditional random fields. During testing each model proposes possible disfluency labels which are then assessed in the presence of global constraints using ILP. Our experimental results show that by using ILP we can improve significantly the performance of our models with negligible cost in processing time. The less training data is available the larger the improvement due to ILP.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Artstein, Ron; Gandhe, Sudeep; Rushforth, Michael; Traum, David
Viability of a Simple Dialogue Act Scheme for a Tactical Questioning Dialogue System Proceedings Article
In: DiaHolmia 2009, the 13th Annual Workshop on the Semantics and Pragmatics of Dialogue, pp. 43–50, Stockholm, Sweden, 2009.
Abstract | Links | BibTeX | Tags: Virtual Humans
@inproceedings{artstein_viability_2009,
title = {Viability of a Simple Dialogue Act Scheme for a Tactical Questioning Dialogue System},
author = {Ron Artstein and Sudeep Gandhe and Michael Rushforth and David Traum},
url = {http://ict.usc.edu/pubs/Viability%20of%20a%20Simple%20Dialogue%20Act%20Scheme%20for%20a%20Tactical%20Questioning%20Dialogue%20System.pdf},
year = {2009},
date = {2009-06-01},
booktitle = {DiaHolmia 2009, the 13th Annual Workshop on the Semantics and Pragmatics of Dialogue},
pages = {43–50},
address = {Stockholm, Sweden},
abstract = {User utterances in a spoken dialogue sys- tem for tactical questioning simulation were matched to a set of dialogue acts gen- erated automatically from a representation of facts as ⟨object, attribute, value⟩ triples and actions as ⟨character, action⟩ pairs. The representation currently covers about 50% of user utterances, and we show that a few extensions can increase coverage to 80% or more. This demonstrates the vi- ability of simple schemes for represent- ing question-answering dialogues in im- plemented systems.},
keywords = {Virtual Humans},
pubstate = {published},
tppubtype = {inproceedings}
}
Sagae, Kenji; Christian, Gwen; DeVault, David; Traum, David
Towards Natural Language Understanding of Partial Speech Recognition Results in Dialogue Systems Proceedings Article
In: Short Paper Proceedings of NAACL HLT 2009, Boulder, CO, 2009.
Abstract | Links | BibTeX | Tags: Virtual Humans
@inproceedings{sagae_towards_2009,
title = {Towards Natural Language Understanding of Partial Speech Recognition Results in Dialogue Systems},
author = {Kenji Sagae and Gwen Christian and David DeVault and David Traum},
url = {http://ict.usc.edu/pubs/Towards%20Natural%20Language%20Understanding%20of%20Partial%20Speech%20Recognition%20Results%20in%20Dialogue%20Systems.pdf},
year = {2009},
date = {2009-06-01},
booktitle = {Short Paper Proceedings of NAACL HLT 2009},
address = {Boulder, CO},
abstract = {We investigate natural language understand- ing of partial speech recognition results to equip a dialogue system with incremental lan- guage processing capabilities for more realis- tic human-computer conversations. We show that relatively high accuracy can be achieved in understanding of spontaneous utterances before utterances are completed.},
keywords = {Virtual Humans},
pubstate = {published},
tppubtype = {inproceedings}
}
Lane, H. Chad; Core, Mark; Gomboc, Dave; Birch, Mike; Hart, John; Rosenberg, Milton
Using Written and Behavioral Data to Detect Evidence of Continuous Lear ning Proceedings Article
In: Proceedings of the User Modeling, Adaptation and Personalization (UMAP) Workshop on Lifelong Learner Modeling, pp. 54–61, Trento, Italy, 2009.
Abstract | Links | BibTeX | Tags:
@inproceedings{lane_using_2009,
title = {Using Written and Behavioral Data to Detect Evidence of Continuous Lear ning},
author = {H. Chad Lane and Mark Core and Dave Gomboc and Mike Birch and John Hart and Milton Rosenberg},
url = {http://ict.usc.edu/pubs/Using_Written_and_Behavioral_Data.pdf},
year = {2009},
date = {2009-06-01},
booktitle = {Proceedings of the User Modeling, Adaptation and Personalization (UMAP) Workshop on Lifelong Learner Modeling},
pages = {54–61},
address = {Trento, Italy},
abstract = {We describe a lifelong learner modeling project that focuses on the use of written and behavioral data to detect patterns of learning over time. Related work in essay analysis and machine learning is discussed. Although primarily focused on isolated learning experiences, we argue there is promise for scaling these techniques up to the lifelong learner modeling problem.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Ghosh, Abhijeet; Chen, Tongbo; Peers, Pieter; Wilson, Cyrus A.; Debevec, Paul
Estimating Specular Roughness and Anisotropy from Second Order Spherical Gradient Illumination Proceedings Article
In: Computer Graphics Forum, pp. 4, 2009.
Abstract | Links | BibTeX | Tags: Graphics
@inproceedings{ghosh_estimating_2009,
title = {Estimating Specular Roughness and Anisotropy from Second Order Spherical Gradient Illumination},
author = {Abhijeet Ghosh and Tongbo Chen and Pieter Peers and Cyrus A. Wilson and Paul Debevec},
url = {http://ict.usc.edu/pubs/Estimating%20Specular%20Roughness%20and%20Anisotropy%20from%20Second%20Order%20Spherical%20Gradient%20Illumination.pdf},
year = {2009},
date = {2009-06-01},
booktitle = {Computer Graphics Forum},
volume = {28},
pages = {4},
abstract = {This paper presents a novel method for estimating specular roughness and tangent vectors, per surface point, from polarized second order spherical gradient illumination patterns. We demonstrate that for isotropic BRDFs, only three second order spherical gradients are sufficient to robustly estimate spatially varying specular roughness. For anisotropic BRDFs, an additional two measurements yield specular roughness and tangent vectors per surface point. We verify our approach with different illumination configurations which project both discrete and continuous fields of gradient illumination. Our technique provides a direct estimate of the per-pixel specular roughness and thus does not require off-line numerical optimization that is typical for the measure-and-fit approach to classical BRDF modeling.},
keywords = {Graphics},
pubstate = {published},
tppubtype = {inproceedings}
}
Akker, Rieks; Traum, David
A comparison of addressee detection methods for multiparty conversations Proceedings Article
In: DiaHolmia 2009, the 13th Annual Workshop on the Semantics and Pragmatics of Dialogue, Stockholm, Sweden, 2009.
Abstract | Links | BibTeX | Tags: Virtual Humans
@inproceedings{op_den_akker_comparison_2009,
title = {A comparison of addressee detection methods for multiparty conversations},
author = {Rieks Akker and David Traum},
url = {http://ict.usc.edu/pubs/A%20comparison%20of%20addressee%20detection%20methods%20for%20multiparty%20conversations.pdf},
year = {2009},
date = {2009-06-01},
booktitle = {DiaHolmia 2009, the 13th Annual Workshop on the Semantics and Pragmatics of Dialogue},
address = {Stockholm, Sweden},
abstract = {Several algorithms have recently been pro- posed for recognizing addressees in a group conversational setting. These al- gorithms can rely on a variety of factors including previous conversational roles, gaze, and type of dialogue act. Both statistical supervised machine learning al- gorithms as well as rule based methods have been developed. In this paper, we compare several algorithms developed for several different genres of multiparty di- alogue, and propose a new synthesis al- gorithm that matches the performance of machine learning algorithms while main- taining the transparency of semantically meaningful rule-based algorithms.},
keywords = {Virtual Humans},
pubstate = {published},
tppubtype = {inproceedings}
}
Flynn, Sheryl; Lange, Belinda; Rizzo, Albert; Valero-Cuevas, F. J.; Baker, L.; Winstein, Carolee J.
An overview of a USC Rehabilitation Engineering Research Center: The use of virtual reality for a range of motor impairments Proceedings Article
In: Virtual Rehabilitation International Conference, 2009.
Abstract | Links | BibTeX | Tags: MedVR
@inproceedings{flynn_overview_2009,
title = {An overview of a USC Rehabilitation Engineering Research Center: The use of virtual reality for a range of motor impairments},
author = {Sheryl Flynn and Belinda Lange and Albert Rizzo and F. J. Valero-Cuevas and L. Baker and Carolee J. Winstein},
url = {http://ict.usc.edu/pubs/An%20overview%20of%20a%20USC%20Rehabilitation%20Engineering%20Research%20Center-%20The%20use%20of%20virtual%20reality%20for%20a%20range%20of%20motor%20impairments.pdf},
year = {2009},
date = {2009-06-01},
booktitle = {Virtual Rehabilitation International Conference},
abstract = {This paper describes the use of Virtual Reality in four projects within a Rehabilitation Engineering Research Center at the University of Southern California. The Research Center aims to develop and assess a range of technologies for people aging with and into a disability. One of the deliverables of this Center will be the development of a Virtual Rehabilitation Toolkit, a series of Virtual Reality video based games for use with a range of impairments for a variety of disabilities including spinal cord injury, traumatic brain injury, stroke, Parkinson's disease, and cerebral palsy.},
keywords = {MedVR},
pubstate = {published},
tppubtype = {inproceedings}
}
Wang, Ning; Gratch, Jonathan
Don't Just Stare at Me! Proceedings Article
In: 28th ACM Conference on Human Factors in Computing Systems, Chicago, IL, 2009.
Abstract | Links | BibTeX | Tags: Virtual Humans
@inproceedings{wang_dont_2009,
title = {Don't Just Stare at Me!},
author = {Ning Wang and Jonathan Gratch},
url = {http://www.ict.usc.edu/pubs/Don't%20Just%20Stare%20at%20Me.pdf},
year = {2009},
date = {2009-06-01},
booktitle = {28th ACM Conference on Human Factors in Computing Systems},
address = {Chicago, IL},
abstract = {Communication is more effective and persuasive when par- ticipants establish rapport. Tickle-Degnen and Rosenthal [57] argue rapport arises when participants exhibit mutual attentiveness, positivity and coordination. In this paper, we investigate how these factors relate to perceptions of rap- port when users interact via avatars in virtual worlds. In this study, participants told a story to what they believed was the avatar of another participant. In fact, the avatar was a computer program that systematically manipulated levels of attentiveness, positivity and coordination. In contrast to Tickel-Degnen and Rosenthal's findings, high-levels of mutual attentiveness alone can dramatically lower percep- tions of rapport in avatar communication. Indeed, an agent that attempted to maximize mutual attention performed as poorly as an agent that was designed to convey boredom. Adding positivity and coordination to mutual attentiveness, on the other hand, greatly improved rapport. This work un- veils the dependencies between components of rapport and informs the design of agents and avatars in computer medi- ated communication.},
keywords = {Virtual Humans},
pubstate = {published},
tppubtype = {inproceedings}
}