Publications
Search
Chiu, Chung-Cheng; Marsella, Stacy C.
Gesture Generation with Low-Dimensional Embeddings Inproceedings
In: Proceedings of the 13th International Conference on Autonomous Agents and Multiagent Systems, pp. 781–788, Paris, France, 2014.
@inproceedings{chiu_gesture_2014,
title = {Gesture Generation with Low-Dimensional Embeddings},
author = {Chung-Cheng Chiu and Stacy C. Marsella},
url = {http://ict.usc.edu/pubs/Gesture%20generation%20with%20low-dimensional%20embeddings.pdf},
year = {2014},
date = {2014-05-01},
booktitle = {Proceedings of the 13th International Conference on Autonomous Agents and Multiagent Systems},
pages = {781--788},
address = {Paris, France},
abstract = {There is a growing demand for embodied agents capable of engaging in face-to-face dialog using the same verbal and nonverbal behavior that people use. The focus of our work is generating coverbal hand gestures for these agents, gestures coupled to the content and timing of speech. A common approach to achieve this is to use motion capture of an actor or hand-crafted animations for each utterance. An alternative machine learning approach that saves development effort is to learn a general gesture controller that can generate behavior for novel utterances. However learning a direct mapping from speech to gesture movement faces the complexity of inferring the relation between the two time series of speech and gesture motion. We present a novel machine learning approach that decomposes the overall learning problem into learning two mappings: from speech to a gestural annotation and from gestural annotation to gesture motion. The combined model learns to synthesize natural gesture animation from speech audio. We assess the quality of generated animations by comparing them with the result generated by a previous approach that learns a direct mapping. Results from a human subject study show that our framework is perceived to be significantly better.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Gratch, Jonathan; Lucas, Gale M.; King, Aisha Aisha; Morency, Louis-Philippe
It’s Only a Computer: The Impact of Human-agent Interaction in Clinical Interviews Inproceedings
In: Proceedings of 13th International Conference on Autonomous Agents and Multiagent Systems, pp. 85–92, International Foundation for Autonomous Agents and Multiagent Systems, Paris, France, 2014.
@inproceedings{gratch_its_2014,
title = {It’s Only a Computer: The Impact of Human-agent Interaction in Clinical Interviews},
author = {Jonathan Gratch and Gale M. Lucas and Aisha Aisha King and Louis-Philippe Morency},
url = {http://ict.usc.edu/pubs/It%E2%80%99s%20only%20a%20computer%20-%20The%20impact%20of%20human-agent%20interaction%20in%20clinical%20interviews.pdf},
year = {2014},
date = {2014-05-01},
booktitle = {Proceedings of 13th International Conference on Autonomous Agents and Multiagent Systems},
pages = {85--92},
publisher = {International Foundation for Autonomous Agents and Multiagent Systems},
address = {Paris, France},
abstract = {Research has begun to explore the use of virtual humans (VHs) in medical interviews [1]. When designed as supportive and “safe” interaction partners, VHs may improve such screenings by encouraging patients to disclose more personal information [2-3]. In medical contexts, patients often feel resistance to selfdisclosure and engage in impression management to be viewed more positively by healthcare providers. This paper provides the first empirical evidence that VHs can reduce such resistance and impression management. In the context of health-screening interviews, we report a study in which participants interacted with a VH that was either teleo-operated by humans (Wizard-of-Oz) or fully-automated (AI). Independently, we manipulated whether participants believed the VH was controlled by humans or automation. As predicted, participants who believed they were interacting with a computer reported lower resistance to selfdisclosure, lower impression management and higher system usability than those who believed they were interacting with a human operator. Whether the virtual human was actually operated by a human or AI only affected ratings of the system’s usability. These results suggest that automated VHs can help overcome a significant barrier to obtaining truthful patient information in medical domains.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Gratch, Jonathan; Artstein, Ron; Lucas, Gale; Stratou, Giota; Scherer, Stefan; Nazarian, Angela; Wood, Rachel; Boberg, Jill; DeVault, David; Marsella, Stacy; Traum, David; Rizzo, Albert; Morency, Louis-Philippe
The Distress Analysis Interview Corpus of human and computer interviews Inproceedings
In: Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC 2014), pp. 3123–3128, LREC, Reykjavik, Iceland, 2014.
@inproceedings{gratch_distress_2014,
title = {The Distress Analysis Interview Corpus of human and computer interviews},
author = {Jonathan Gratch and Ron Artstein and Gale Lucas and Giota Stratou and Stefan Scherer and Angela Nazarian and Rachel Wood and Jill Boberg and David DeVault and Stacy Marsella and David Traum and Albert Rizzo and Louis-Philippe Morency},
url = {http://ict.usc.edu/pubs/The%20Distress%20Analysis%20Interview%20Corpus%20of%20human%20and%20computer%20interviews.pdf},
year = {2014},
date = {2014-05-01},
booktitle = {Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC 2014)},
pages = {3123--3128},
publisher = {LREC},
address = {Reykjavik, Iceland},
abstract = {The Distress Analysis Interview Corpus (DAIC) contains clinical interviews designed to support the diagnosis of psychological distress conditions such as anxiety, depression, and post traumatic stress disorder. The interviews are conducted by humans, human controlled agents and autonomous agents, and the participants include both distressed and non-distressed individuals. Data collected include audio and video recordings and extensive questionnaire responses; parts of the corpus have been transcribed and annotated for a variety of verbal and non-verbal features. The corpus has been used to support the creation of an automated interviewer agent, and for research on the automatic identification of psychological distress.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Malandrakis, Nikolaos; Potamianos, Alexandros; Hsu, Kean J.; Babeva, Kalina N.; Feng, Michelle C.; Davison, Gerald C.; Narayanan, Shrikanth
AFFECTIVE LANGUAGE MODEL ADAPTATION VIA CORPUS SELECTION Inproceedings
In: proceedings of ICASSP, Florence, Italy, 2014.
@inproceedings{malandrakis_affective_2014,
title = {AFFECTIVE LANGUAGE MODEL ADAPTATION VIA CORPUS SELECTION},
author = {Nikolaos Malandrakis and Alexandros Potamianos and Kean J. Hsu and Kalina N. Babeva and Michelle C. Feng and Gerald C. Davison and Shrikanth Narayanan},
url = {http://ict.usc.edu/pubs/Affective%20language%20model%20adaptation%20via%20corpus%20selection.pdf},
year = {2014},
date = {2014-05-01},
booktitle = {proceedings of ICASSP},
address = {Florence, Italy},
abstract = {Motivated by methods used in language modeling and grammar induction, we propose the use of pragmatic constraints and perplexity as criteria to filter the unlabeled data used to generate the semantic similarity model. We investigate unsupervised adaptation algorithms of the semantic-affective models proposed in [1, 2]. Affective ratings at the utterance level are generated based on an emotional lexicon, which in turn is created using a semantic (similarity) model estimated over raw, unlabeled text. The proposed adaptation method creates task-dependent semantic similarity models and task- dependent word/term affective ratings. The proposed adaptation algorithms are tested on anger/distress detection of transcribed speech data and sentiment analysis in tweets showing significant relative classification error reduction of up to 10%.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Vaz, Colin; Tsiartas, Andreas; Narayanan, Shrikanth
ENERGY-CONSTRAINED MINIMUM VARIANCE RESPONSE FILTER FOR ROBUST VOWEL SPECTRAL ESTIMATION Inproceedings
In: Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on, pp. 6275–6279, IEEE, 2014.
@inproceedings{vaz_energy-constrained_2014,
title = {ENERGY-CONSTRAINED MINIMUM VARIANCE RESPONSE FILTER FOR ROBUST VOWEL SPECTRAL ESTIMATION},
author = {Colin Vaz and Andreas Tsiartas and Shrikanth Narayanan},
url = {http://ict.usc.edu/pubs/Energy-Constrained%20Minimum%20Variance%20Response%20Filter%20for%20Robust%20Vowel%20Spectral%20Estimation.pdf},
year = {2014},
date = {2014-05-01},
booktitle = {Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on},
pages = {6275--6279},
publisher = {IEEE},
abstract = {We propose the energy-constrained minimum-variance response (ECMVR) filter to perform robust spectral estimation of vowels. We modify the distortionless constraint of the minimum-variance distortionless response (MVDR) filter and add an energy constraint to its formulation to mitigate the influence of noise on the speech spectrum. We test our ECMVR filter on a vowel classification task with different background noises at various SNR levels. Results show that vowels are classified more accurately in certain noises using MFCC and PLP features extracted from the ECMVR spectrum compared to using features extracted from the FFT and MVDR spectra. Index Terms: frequency estimation, MVDR, robust signal processing, spectral estimation.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Degottex, Gilles; Kane, John; Drugman, Thomas; Raitio, Tuomo; Scherer, Stefan
COVAREP - A collaborative voice analysis repository for speech technologies Inproceedings
In: Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2014), pp. 960–964, IEEE, Florence, Italy, 2014.
@inproceedings{degottex_covarep_2014,
title = {COVAREP - A collaborative voice analysis repository for speech technologies},
author = {Gilles Degottex and John Kane and Thomas Drugman and Tuomo Raitio and Stefan Scherer},
url = {http://ict.usc.edu/pubs/COVAREP%20%e2%80%93%20A%20COLLABORATIVE%20VOICE%20ANALYSIS%20REPOSITORY%20FOR%20SPEECH%20TECHNOLOGIES.pdf},
year = {2014},
date = {2014-05-01},
booktitle = {Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2014)},
pages = {960--964},
publisher = {IEEE},
address = {Florence, Italy},
abstract = {Speech processing algorithms are often developed demonstrating improvements over the state-of-the-art, but sometimes at the cost of high complexity. This makes algorithm reimplementations based on literature difficult, and thus reliable comparisons between published results and current work are hard to achieve. This paper presents a new collaborative and freely available repository for speech processing algorithms called COVAREP, which aims at fast and easy access to new speech processing algorithms and thus facilitating research in the field. We envisage that COVAREP will allow more reproducible research by strengthening complex implementations through shared contributions and openly available code which can be discussed, commented on and corrected by the community. Presently COVAREP contains contributions from five distinct laboratories and we encourage contributions from across the speech processing research field. In this paper, we provide an overview of the current offerings of COVAREP and also include a demonstration of the algorithms through an emotion classification experiment.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Chollet, Mathieu; Stratou, Giota; Shapiro, Ari; Morency, Louis-Philippe; Scherer, Stefan
An Interactive Virtual Audience Platform for Public Speaking Training Inproceedings
In: Proceedings of International Conference on Autonomous Agents and Multiagent Systems (AAMAS), pp. 1657–1658, ACM, Paris, France, 2014.
@inproceedings{chollet_interactive_2014,
title = {An Interactive Virtual Audience Platform for Public Speaking Training},
author = {Mathieu Chollet and Giota Stratou and Ari Shapiro and Louis-Philippe Morency and Stefan Scherer},
url = {http://ict.usc.edu/pubs/An%20Interactive%20Virtual%20Audience%20Platform%20for%20Public%20Speaking%20Training.pdf},
year = {2014},
date = {2014-05-01},
booktitle = {Proceedings of International Conference on Autonomous Agents and Multiagent Systems (AAMAS)},
pages = {1657--1658},
publisher = {ACM},
address = {Paris, France},
abstract = {We have developed an interactive virtual audience platform for public speaking training. Users' public speaking behavior is automatically analyzed using audiovisual sensors. The virtual characters display indirect feedback depending on user's behavior descriptors correlated with public speaking performance. We used the system to collect a dataset of public speaking performances in di⬚erent training conditions.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
DeVault, David; Artstein, Ron; Benn, Grace; Dey, Teresa; Fast, Edward; Gainer, Alesia; Georgila, Kallirroi; Gratch, Jonathan; Hartholt, Arno; Lhommet, Margaux; Lucas, Gale; Marsella, Stacy C.; Fabrizio, Morbini; Nazarian, Angela; Scherer, Stefan; Stratou, Giota; Suri, Apar; Traum, David; Wood, Rachel; Xu, Yuyu; Rizzo, Albert; Morency, Louis-Philippe
SimSensei Kiosk: A Virtual Human Interviewer for Healthcare Decision Support Inproceedings
In: Proceedings of the 13th Inter-national Conference on Autonomous Agents and Multiagent Systems (AAMAS 2014), pp. 1061–1068, International Foundation for Autonomous Agents and Multiagent Systems, Paris, France, 2014.
@inproceedings{devault_simsensei_2014,
title = {SimSensei Kiosk: A Virtual Human Interviewer for Healthcare Decision Support},
author = {David DeVault and Ron Artstein and Grace Benn and Teresa Dey and Edward Fast and Alesia Gainer and Kallirroi Georgila and Jonathan Gratch and Arno Hartholt and Margaux Lhommet and Gale Lucas and Stacy C. Marsella and Morbini Fabrizio and Angela Nazarian and Stefan Scherer and Giota Stratou and Apar Suri and David Traum and Rachel Wood and Yuyu Xu and Albert Rizzo and Louis-Philippe Morency},
url = {https://dl.acm.org/citation.cfm?id=2617415},
year = {2014},
date = {2014-05-01},
booktitle = {Proceedings of the 13th Inter-national Conference on Autonomous Agents and Multiagent Systems (AAMAS 2014)},
pages = {1061--1068},
publisher = {International Foundation for Autonomous Agents and Multiagent Systems},
address = {Paris, France},
abstract = {We present SimSensei Kiosk, an implemented virtual human interviewer designed to create an engaging face-to-face inter-action where the user feels comfortable talking and sharing information. SimSensei Kiosk is also designed to create in- teractional situations favorable to the automatic assessment of distress indicators, de_ned as verbal and nonverbal behav- iors correlated with depression, anxiety or post-traumatic stress disorder (PTSD). In this paper, we summarize the de- sign methodology, performed over the past two years, which is based on three main development cycles: (1) analysis of face-to-face human interactions to identify potential distress indicators, dialogue policies and virtual human gestures, (2) development and analysis of a Wizard-of-Oz prototype sys- tem where two human operators were deciding the spoken and gestural responses, and (3) development of a fully au- tomatic virtual interviewer able to engage users in 15-25 minute interactions. We show the potential of our fully auto- matic virtual human interviewer in a user study, and situate its performance in relation to the Wizard-of-Oz prototype.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Kumar, Naveen; Segbroeck, Maarten Van; Audhkhasi, Kartik; Drotár, Peter; Narayanan, Shrikanth S.
Fusion of Diverse Denoising Systems for Robust Automatic Speech Recognition Inproceedings
In: Proceedings of IEEE International Conference on Audio, Speech and Signal Processing (ICASSP), 2014.
@inproceedings{kumar_fusion_2014,
title = {Fusion of Diverse Denoising Systems for Robust Automatic Speech Recognition},
author = {Naveen Kumar and Maarten Van Segbroeck and Kartik Audhkhasi and Peter Drotár and Shrikanth S. Narayanan},
url = {http://ict.usc.edu/pubs/Fusion%20of%20Diverse%20denoising%20systems%20for%20Robust%20Automatic%20Speech%20Recognition.pdf},
year = {2014},
date = {2014-05-01},
booktitle = {Proceedings of IEEE International Conference on Audio, Speech and Signal Processing (ICASSP)},
abstract = {We present a framework for combining different denoising front-ends for robust speech enhancement for recognition in noisy conditions. This is contrasted against results of optimally fusing diverse parameter settings for a single denoising algorithm. All frontends in the latter case exploit the same denoising algorithm, which combines harmonic decomposition, with noise estimation and spectral subtraction. The set of associated parameters involved in these steps are dependent on the noise conditions. Rather than explicitly tuning them, we suggest a strategy that tries to account for the trade-off between average word error rate and diversity to find an optimal subset of these parameter settings. We present the results on Aurora4 database and also compare against traditional speech enhancement methods e.g. Wiener filtering and spectral subtraction.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Shapiro, Ari; Feng, Andrew; Wang, Ruizhe; Li, Hao; Bolas, Mark; Medioni, Gerard; Suma, Evan
Rapid avatar capture and simulation using commodity depth sensors Journal Article
In: Computer Animation and Virtual Worlds, vol. 25, no. 3-4, pp. 201–211, 2014, ISSN: 15464261.
@article{shapiro_rapid_2014,
title = {Rapid avatar capture and simulation using commodity depth sensors},
author = {Ari Shapiro and Andrew Feng and Ruizhe Wang and Hao Li and Mark Bolas and Gerard Medioni and Evan Suma},
url = {http://ict.usc.edu/pubs/Rapid%20Avatar%20Capture%20and%20Simulation%20Using%20Commodity%20Depth%20Sensors.pdf},
doi = {10.1002/cav.1579},
issn = {15464261},
year = {2014},
date = {2014-05-01},
journal = {Computer Animation and Virtual Worlds},
volume = {25},
number = {3-4},
pages = {201--211},
abstract = {We demonstrate a method of acquiring a 3D model of a human using commodity scanning hardware and then controlling that 3D figure in a simulated environment in only a few minutes. The model acquisition requires four static poses taken at 90 degree angles relative to each other. The 3D model is then given a skeleton and smooth binding information necessary for control and simulation. The 3D models that are captured are suitable for use in applications where recognition and distinction among characters by shape, form, or clothing is important, such as small group or crowd simulations or other socially oriented applications. Because of the speed at which a human figure can be captured and the low hardware requirements, this method can be used to capture, track, and model human figures as their appearances change over time.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Can, Dogan; Gibson, James; Vaz, Colin; Georgiou, Panayiotis G.; Narayanan, Shrikanth S.
Barista: A framework for concurrent speech processing by usc-sail Inproceedings
In: Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on, pp. 3306–3310, IEEE, 2014.
@inproceedings{can_barista_2014,
title = {Barista: A framework for concurrent speech processing by usc-sail},
author = {Dogan Can and James Gibson and Colin Vaz and Panayiotis G. Georgiou and Shrikanth S. Narayanan},
url = {http://ict.usc.edu/pubs/Barista%20-%20A%20Framework%20for%20Concurrent%20Speech%20Processing%20by%20USC-SAIL.pdf},
year = {2014},
date = {2014-05-01},
booktitle = {Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on},
pages = {3306--3310},
publisher = {IEEE},
abstract = {We present Barista, an open-source framework for concurrent speech processing based on the Kaldi speech recognition toolkit and the libcppa actor library. With Barista, we aim to provide an easy-to-use, extensible framework for constructing highly customizable concurrent (and/or distributed) networks for a variety of speech processing tasks. Each Barista network specifies a flow of data between simple actors, concurrent entities communicating by message passing, modeled after Kaldi tools. Leveraging the fast and reliable concurrency and distribution mechanisms provided by libcppa, Barista lets demanding speech processing tasks, such as real-time speech recognizers and complex training workflows, to be scheduled and executed on parallel (and/or distributed) hardware. Barista is released under the Apache License v2.0.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Krum, David M.; Kang, Sin-Hwa; Bolas, Mark
Virtual Coaches over Mobile Video Inproceedings
In: Proceedingsof International Conference on Computer Animation and Social Agents (CASA), 2014.
@inproceedings{krum_virtual_2014,
title = {Virtual Coaches over Mobile Video},
author = {David M. Krum and Sin-Hwa Kang and Mark Bolas},
url = {http://ict.usc.edu/pubs/Virtual%20Coaches%20over%20Mobile%20Video.pdf},
year = {2014},
date = {2014-05-01},
booktitle = {Proceedingsof International Conference on Computer Animation and Social Agents (CASA)},
abstract = {We hypothesize that the context of a smartphone, how a virtual human is presented within a smartphone app, and indeed, the nature of that app, can profoundly affect how the virtual human is perceived by a real human. We believe that virtual humans, presented over video chat services (such as Skype) and delivered using mobile phones, can be an effective way to deliver coaching applications. We propose to build a prototype system that allows virtual humans to initiate and receive Skype calls. This hardware will enable broadcast of the audio and video imagery of a character. Using this platform and a virtual human, we will conduct two user studies. The first study will examine factors involved in making a mobile video based character seem engaging and “real”. This study will examine how character appearance and the artifacts of the communication channel, such as video and audio quality, can affect rapport with a virtual human. The second study will examine ways to maintain a long-term relationship with a character, leveraging the character’s ability to call and interact with a real human over a longer period of time. These studies will help develop design guidelines for presenting virtual humans over mobile video.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Miller, Chreston; Quek, Francis; Morency, Louis-Philippe
Search Strategies for Pattern Identification in Multimodal Data: Three Case Studies Inproceedings
In: pp. 273–280, ACM Press, 2014, ISBN: 978-1-4503-2782-4.
@inproceedings{miller_search_2014,
title = {Search Strategies for Pattern Identification in Multimodal Data: Three Case Studies},
author = {Chreston Miller and Francis Quek and Louis-Philippe Morency},
url = {http://ict.usc.edu/pubs/Search%20Strategies%20for%20Pattern%20Identification%20in%20Multimodal%20Data%20Three%20Case%20Studies.pdf},
doi = {10.1145/2578726.2578761},
isbn = {978-1-4503-2782-4},
year = {2014},
date = {2014-04-01},
pages = {273--280},
publisher = {ACM Press},
abstract = {The analysis of multimodal data benefits from meaningful search and retrieval. This paper investigates strategies of searching multimodal data for event patterns. Through three longitudinal case studies, we observed researchers exploring and identifying event patterns in multimodal data. The events were extracted from different multimedia signal sources ranging from annotated video transcripts to interaction logs. Each researcher’s data has varying temporal characteristics (e.g., sparse, dense, or clustered) that posed several challenges for identifying relevant patterns. We identify unique search strategies and better understand the aspects that contributed to each.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
McAlinden, Ryan; Pynadath, David V.; Hill, Randall W.
UrbanSim: Using Social Simulation to Train for Stability Operations Incollection
In: Understanding Megacities with the Reconnaissance, Surveillance, and Intelligence Paradigm, 2014.
@incollection{mcalinden_urbansim_2014,
title = {UrbanSim: Using Social Simulation to Train for Stability Operations},
author = {Ryan McAlinden and David V. Pynadath and Randall W. Hill},
url = {http://ict.usc.edu/pubs/UrbanSim%20-%20Using%20Social%20Simulation%20to%20Train%20for%20Stability%20Operations.pdf},
year = {2014},
date = {2014-04-01},
booktitle = {Understanding Megacities with the Reconnaissance, Surveillance, and Intelligence Paradigm},
abstract = {As the United States reorients itself towards to a period of reduced military capacity and away from large‐footprint military engagements, there is an imperative to keep commanders and decision‐makers mentally sharp and prepared for the next ‘hot spot.’ One potential hot spot, megacities, presents a unique set of challenges due to their expansive, often interwoven ethnographic landscapes, and their overall lack of understanding by many western experts. Social simulation using agent‐based models is one approach for furthering our understanding of distant societies and their security implications, and for preparing leaders to engage these populations if and when the need arises. Over the past ten years, the field of social simulation has become decidedly cross‐discipline, including academics and practitioners from the fields of sociology, anthropology, psychology, artificial intelligence and engineering. This has led to an unparalleled advancement in social simulation theory and practice, and as new threats evolve to operate within dense but expansive urban environments, social simulation has a unique opportunity to shape our perspectives and develop knowledge that may otherwise be difficult to obtain. This article presents a social simulation‐based training application (UrbanSim) developed by the University of Southern California’s Institute for Creative Technologies (USC‐ICT) in partnership with the US Army’s School for Command Preparation (SCP). UrbanSim has been in‐use since 2009 to help Army commanders understand and train for missions in complex, uncertain environments. The discussion describes how the social simulation‐based training application was designed to develop and hone commanders' skills for conducting missions in environs with multifaceted social, ethnic and political fabrics. We present a few considerations when attempting to recreate dense, rapidly growing population centers, and how the integration of real‐world data into social simulation frameworks can add a level of realism and understanding not possible even a few years ago.},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
Hobbs, Jerry R.; Gordon, Andrew
Axiomatizing Complex Concepts from Fundamentals Incollection
In: Hutchison, David; Kanade, Takeo; Kittler, Josef; Kleinberg, Jon M.; Mattern, Friedemann; Mitchell, John C.; Naor, Moni; Nierstrasz, Oscar; Rangan, C. Pandu; Steffen, Bernhard; Sudan, Madhu; Terzopoulos, Demetri; Tygar, Doug; Vardi, Moshe Y.; Weikum, Gerhard; Gelbukh, Alexander (Ed.): Computational Linguistics and Intelligent Text Processing, pp. 351–365, Springer Berlin Heidelberg, Berlin, Heidelberg, 2014, ISBN: 978-3-642-54905-2 978-3-642-54906-9.
@incollection{hobbs_axiomatizing_2014,
title = {Axiomatizing Complex Concepts from Fundamentals},
author = {Jerry R. Hobbs and Andrew Gordon},
editor = {David Hutchison and Takeo Kanade and Josef Kittler and Jon M. Kleinberg and Friedemann Mattern and John C. Mitchell and Moni Naor and Oscar Nierstrasz and C. Pandu Rangan and Bernhard Steffen and Madhu Sudan and Demetri Terzopoulos and Doug Tygar and Moshe Y. Vardi and Gerhard Weikum and Alexander Gelbukh},
url = {http://link.springer.com/10.1007/978-3-642-54906-9_29},
isbn = {978-3-642-54905-2 978-3-642-54906-9},
year = {2014},
date = {2014-04-01},
booktitle = {Computational Linguistics and Intelligent Text Processing},
pages = {351--365},
publisher = {Springer Berlin Heidelberg},
address = {Berlin, Heidelberg},
abstract = {We have been engaged in the project of encoding commonsense theories of cognition, or how we think we think, in a logical representation. In this paper we use the concept of a “serious threat” as our prime example, and examine the infrastructure required for capturing the meaning of this complex concept. It is one of many examples we could have used, but it is particularly interesting because building up to this concept from fundamentals, such as causality and scalar notions, highlights a number of representational issues that have to be faced along the way, where the complexity of the target concepts strongly influences how we resolve those issues. We first describe our approach to definition, defeasibility, and reification, where hard decisions have to bemade to get the enterprise off the ground.We then sketch our approach to causality, scalar notions, goals, and importance. Finally we use all this to characterize what it is to be a serious threat. All of this is necessarily sketchy, but the key ideas essential to the target concept should be clear.},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
Audhkhasi, Kartik; Zavou, Andreas M.; Georgiou, Panayiotis G.; Narayanan, Shrikanth S.
Theoretical Analysis of Diversity in an Ensemble of Automatic Speech Recognition Systems Journal Article
In: IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 22, no. 3, pp. 711–726, 2014, ISSN: 2329-9290, 2329-9304.
@article{audhkhasi_theoretical_2014,
title = {Theoretical Analysis of Diversity in an Ensemble of Automatic Speech Recognition Systems},
author = {Kartik Audhkhasi and Andreas M. Zavou and Panayiotis G. Georgiou and Shrikanth S. Narayanan},
url = {http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6727393},
doi = {10.1109/TASLP.2014.2303295},
issn = {2329-9290, 2329-9304},
year = {2014},
date = {2014-03-01},
journal = {IEEE/ACM Transactions on Audio, Speech, and Language Processing},
volume = {22},
number = {3},
pages = {711--726},
abstract = {Diversity or complementarity of automatic speech recognition (ASR) systems is crucial for achieving a reduction in word error rate (WER) upon fusion using the ROVER algorithm. We present a theoretical proof explaining this often-observed link between ASR system diversity and ROVER performance. This is in contrast to many previous works that have only presented empirical evidence for this link or have focused on designing diverse ASR systems using intuitive algorithmic modifications. We prove that the WER of the ROVER output approximately decomposes into a difference of the average WER of the individual ASR systems and the average WER of the ASR systems with respect to the ROVER output. We refer to the latter quantity as the diversity of the ASR system ensemble because it measures the spread of the ASR hypotheses about the ROVER hypothesis. This result explains the trade-off between the WER of the individual systems and the diversity of the ensemble. We support this result through ROVER experiments using multiple ASR systems trained on standard data sets with the Kaldi toolkit. We use the proposed theorem to explain the lower WERs obtained by ASR confidence-weighted ROVER as compared to word frequency-based ROVER. We also quantify the reduction in ROVER WER with increasing diversity of the N- best list. We finally present a simple discriminative framework for jointly training multiple diverse acoustic models (AMs) based on the proposed theorem. Our framework generalizes and provides a theoretical basis for some recent intuitive modifications to well-known discriminative training criterion for training diverse AMs.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Hill, Randall W.
Virtual Reality and Leadership Development Incollection
In: Using Experience to Develop Leadership Talent: How Organizations Leverage On-The-Job Development, pp. 286–312, John Wiley & Sons, Inc., 2014, ISBN: 978-1-118-76783-2.
@incollection{hill_virtual_2014,
title = {Virtual Reality and Leadership Development},
author = {Randall W. Hill},
url = {http://www.amazon.com/dp/1118767837/ref=cm_sw_su_dp},
isbn = {978-1-118-76783-2},
year = {2014},
date = {2014-03-01},
booktitle = {Using Experience to Develop Leadership Talent: How Organizations Leverage On-The-Job Development},
pages = {286--312},
publisher = {John Wiley & Sons, Inc.},
series = {J-B SIOP Professional Practice Series (Book 1)},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
Thomas, Jerald; Bashyal, Raghav; Goldstein, Samantha; Suma, Evan
MuVR: A Multi-user Virtual Reality Platform Inproceedings
In: IEEE Virtual Reality 2014, pp. 115–116, IEEE, Minneapolis, Minnesota, 2014.
@inproceedings{thomas_muvr_2014,
title = {MuVR: A Multi-user Virtual Reality Platform},
author = {Jerald Thomas and Raghav Bashyal and Samantha Goldstein and Evan Suma},
url = {http://ict.usc.edu/pubs/MuVR%20-%20A%20Multi-user%20Virtual%20Reality%20Platform.pdf},
year = {2014},
date = {2014-03-01},
booktitle = {IEEE Virtual Reality 2014},
pages = {115--116},
publisher = {IEEE},
address = {Minneapolis, Minnesota},
abstract = {Consumer adoption of virtual reality technology has historically been held back by poor accessibility, the lack of intuitive multi-user capabilities, dependence on external infrastructure for rendering and tracking, and the amount of time and effort required to enter virtual reality systems. This poster presents the current status of our work creating MuVR, a Multi-User Virtual Reality platform that seeks to overcome these hindrances. The MuVR project comprises four main goals: scalable and easy to use multi-user capabilities, portable and self-contained hardware, a rapidly deployable system, and ready accessibility to others. We provide a description of the platform we developed to address these goals and discuss potential directions for future work.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Sukthankar, Gita; Goldman, Robert P.; Geib, Christopher; Pynadath, David V.; Bui, Hung
Plan, Activity, and Intent Recognition: Theory and Practice Book
Morgan Kaufmann, 2014, ISBN: 0-12-398532-3.
@book{sukthankar_plan_2014,
title = {Plan, Activity, and Intent Recognition: Theory and Practice},
author = {Gita Sukthankar and Robert P. Goldman and Christopher Geib and David V. Pynadath and Hung Bui},
url = {http://www.amazon.com/Plan-Activity-Intent-Recognition-Practice/dp/0123985323/ref=sr_1_1?s=books&ie=UTF8&qid=1408747877&sr=1-1&keywords=Plan%2C+Activity%2C+and+Intent+Recognition%3A+Theory+and+Practice},
isbn = {0-12-398532-3},
year = {2014},
date = {2014-03-01},
publisher = {Morgan Kaufmann},
keywords = {},
pubstate = {published},
tppubtype = {book}
}
Shapiro, Ari; Feng, Andrew; Wang, Ruizhe; Medioni, Gerard; Bolas, Mark; Suma, Evan A.
Automatic Acquisition and Animation of Virtual Avatars Inproceedings
In: Virtual Reality (VR), 2014 iEEE, pp. 185–186, IEEE, Minneapolis, Minnesota, 2014, ISBN: 978-1-4799-2871-2.
@inproceedings{shapiro_automatic_2014,
title = {Automatic Acquisition and Animation of Virtual Avatars},
author = {Ari Shapiro and Andrew Feng and Ruizhe Wang and Gerard Medioni and Mark Bolas and Evan A. Suma},
url = {http://ict.usc.edu/pubs/Automatic%20acquisition%20and%20animation%20of%20virtual%20avatars.pdf},
doi = {10.1109/VR.2014.6802113},
isbn = {978-1-4799-2871-2},
year = {2014},
date = {2014-03-01},
booktitle = {Virtual Reality (VR), 2014 iEEE},
pages = {185--186},
publisher = {IEEE},
address = {Minneapolis, Minnesota},
abstract = {The USC Institute for Creative Technologies will demonstrate a pipline for automatic reconstruction and animation of lifelike 3D avatars acquired by rotating the user's body in front of a single Microsoft Kinect sensor. Based on a fusion of state-of-the-art techniques in computer vision, graphics, and animation, this approach can produce a fully rigged character model suitable for real-time virtual environments in less than four minutes.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Filter
2000
Gratch, Jonathan
Human-like behavior, alas, demands human-like intellect Inproceedings
In: Agents 2000 Workshop on Achieving Human-like Behavior in Interactive Animated Agents, Barcelona, Spain, 2000.
Links | BibTeX | Tags: Virtual Humans
@inproceedings{gratch_human-like_2000,
title = {Human-like behavior, alas, demands human-like intellect},
author = {Jonathan Gratch},
url = {http://ict.usc.edu/pubs/Human-like%20behavior%20alas%20demands%20human-like%20intellect.pdf},
year = {2000},
date = {2000-06-01},
booktitle = {Agents 2000 Workshop on Achieving Human-like Behavior in Interactive Animated Agents},
address = {Barcelona, Spain},
keywords = {Virtual Humans},
pubstate = {published},
tppubtype = {inproceedings}
}
Moutchtaris, Athanasios; Reveliotis, Panagiotis; Kyriakakis, Chris
Inverse Filter Design for Immersive Audio Rendering Over Loudspeakers Journal Article
In: IEEE Transactions on Multimedia, vol. 2, no. 2, pp. 77–87, 2000.
Abstract | Links | BibTeX | Tags:
@article{moutchtaris_inverse_2000,
title = {Inverse Filter Design for Immersive Audio Rendering Over Loudspeakers},
author = {Athanasios Moutchtaris and Panagiotis Reveliotis and Chris Kyriakakis},
url = {http://ict.usc.edu/pubs/Inverse%20Filter%20Design%20for%20Immersive%20Audio%20Rendering%20Over%20Loudspeakers.pdf},
year = {2000},
date = {2000-06-01},
journal = {IEEE Transactions on Multimedia},
volume = {2},
number = {2},
pages = {77--87},
abstract = {Immersive audio systems can be used to render virtual sound sources in three-dimensional (3-D) space around a listener. This is achieved by simulating the head-related transfer function (HRTF) amplitude and phase characteristics using digital filters. In this paper, we examine certain key signal processing considerations in spatial sound rendering over headphones and loudspeakers. We address the problem of crosstalk inherent in loudspeaker rendering and examine two methods for implementing crosstalk cancellation and loudspeaker frequency response inversion in real time. We demonstrate that it is possible to achieve crosstalk cancellation of 30 dB using both methods, but one of the two (the Fast RLS Transversal Filter Method) offers a significant advantage in terms of computational efficiency. Our analysis is easily extendable to nonsymmetric listening positions and moving listeners.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Hill, Randall W.; Gratch, Jonathan; Rosenbloom, Paul
Flexible Group Behavior: Virtual Commanders for Synthetic Battlespaces Inproceedings
In: Proceedings of the 4th International Conference on Autonomous Agents, Barcelona, Spain, 2000.
Abstract | Links | BibTeX | Tags: CogArch, Cognitive Architecture, Social Simulation, Virtual Humans
@inproceedings{hill_flexible_2000,
title = {Flexible Group Behavior: Virtual Commanders for Synthetic Battlespaces},
author = {Randall W. Hill and Jonathan Gratch and Paul Rosenbloom},
url = {http://ict.usc.edu/pubs/Flexible%20Group%20Behavior-%20Virtual%20Commanders%20for%20Synthetic%20Battlespaces.pdf},
year = {2000},
date = {2000-06-01},
booktitle = {Proceedings of the 4th International Conference on Autonomous Agents},
address = {Barcelona, Spain},
abstract = {This paper describes a project to develop autonomous commander agents for synthetic battlespaces. The commander agents plan missions, monitor their execution, and replan when necessary. To reason about the social aspects of group behavior, the commanders take various social stances that enable them to collaborate with friends, exercise or defer to authority, and thwart their foes. The purpose of this paper is to describe these capabilities and how they came to be through a series of lessons learned while developing autonomous agents for this domain.},
keywords = {CogArch, Cognitive Architecture, Social Simulation, Virtual Humans},
pubstate = {published},
tppubtype = {inproceedings}
}
Kim, Youngjun; Hill, Randall W.; Gratch, Jonathan
How Long Can an Agent Look Away From a Target? Inproceedings
In: 9th Conference on Computer Generated Forces and Behavioral Representation, 2000.
Abstract | Links | BibTeX | Tags: Virtual Humans
@inproceedings{kim_how_2000,
title = {How Long Can an Agent Look Away From a Target?},
author = {Youngjun Kim and Randall W. Hill and Jonathan Gratch},
url = {http://ict.usc.edu/pubs/how%20long%20can%20you%20look%20away%20from%20a%20target.pdf},
year = {2000},
date = {2000-05-01},
booktitle = {9th Conference on Computer Generated Forces and Behavioral Representation},
abstract = {Situation awareness (SA) is the perception of the elements in the environment within a volume of time and space, the comprehension of their meaning, and the projection of their status in the near future [3]. Although the impact of situation awareness and assessment on humans in complex systems is clear, no one theory for SA has been developed. A critical aspect of the SA problem is that agents must construct an overall view of a dynamically changing world using limited sensor channels. For instance, a (virtual) pilot, who visually tracks the location and direction of several vehicles that he cannot see simultaneously, must shift its visual field of view to scan the environment and to sense the situation involved. How he directs his attention, for how long, and how he efficiently reacquires targets is the central question we address in this paper. We describe the perceptual coordination that helps a virtual pilot efficiently track one or more objects. In SA, it is important for a virtual pilot having a limited visual field of view to gather more information from its environment and to choose appropriate actions to take in the environment without losing the target.},
keywords = {Virtual Humans},
pubstate = {published},
tppubtype = {inproceedings}
}
Georgiou, Panayiotis G.; Kyriakakis, Chris
A Multiple Input Single Output Model for Rendering Virtual Sound Sources in Real Time Inproceedings
In: Proceedings of ICME 2000, New York, NY, 2000.
Abstract | Links | BibTeX | Tags:
@inproceedings{georgiou_multiple_2000,
title = {A Multiple Input Single Output Model for Rendering Virtual Sound Sources in Real Time},
author = {Panayiotis G. Georgiou and Chris Kyriakakis},
url = {http://ict.usc.edu/pubs/A%20MULTIPLE%20INPUT%20SINGLE%20OUTPUT%20MODEL%20FOR%20RENDERING%20VIRTUAL%20SOUND%20SOURCES%20IN%20REAL%20TIME.pdf},
year = {2000},
date = {2000-01-01},
booktitle = {Proceedings of ICME 2000},
address = {New York, NY},
abstract = {Accurate localization of sound in 3-D space is based on variations in the spectrum of sound sources. These variations arise mainly from reflection and diffraction effects caused by the pinnae and are described through a set of Head-Related Transfer Functions (HRTF’s) that are unique for each azimuth and elevation angle. A virtual sound source can be rendered in the desired location by filtering with the corresponding HRTF for each ear. Previous work on HRTF modeling has mainly focused on the methods that attempt to model each transfer function individually. These methods are generally computationally-complex and cannot be used for real-time spatial rendering of multiple moving sources. In this work we provide an alternative approach, which uses a multiple input single output state space system to creat a combined model of the HRTF’s for all directions. This method exploits the similarities among the different HRTF’s to achieve a significant reduction in the model size with a minimum loss of accuracy.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Gratch, Jonathan
Èmile: Marshalling Passions in Training and Education Inproceedings
In: Proceedings of the 4th International Conference on Autonomous Agents, pp. 325–332, Barcelona, Spain, 2000.
Abstract | Links | BibTeX | Tags: Virtual Humans
@inproceedings{gratch_emile_2000,
title = {Èmile: Marshalling Passions in Training and Education},
author = {Jonathan Gratch},
url = {http://ict.usc.edu/pubs/Emile-%20Marshalling%20Passions%20in%20Training%20and%20Education.pdf},
year = {2000},
date = {2000-01-01},
booktitle = {Proceedings of the 4th International Conference on Autonomous Agents},
pages = {325--332},
address = {Barcelona, Spain},
abstract = {Emotional reasoning can be an important contribution to automated tutoring and training systems. This paper describes �mile, a model of emotional reasoning that builds upon existing approaches and significantly generalizes and extends their capabilities. The main contribution is to show how an explicit planning model allows a more general treatment of several stages of the reasoning process. The model supports educational applications by allowing agents to appraise the emotional significance of events as they relate to students' (or their own) plans and goals, model and predict the emotional state of others, and alter behavior accordingly.},
keywords = {Virtual Humans},
pubstate = {published},
tppubtype = {inproceedings}
}
Gratch, Jonathan
Modeling the Interplay Between Emotion and Decision-Making Inproceedings
In: Proceedings of the 9th Conference on Computer Generated Forces and Behavioral Representation, 2000.
Abstract | Links | BibTeX | Tags: Virtual Humans
@inproceedings{gratch_modeling_2000,
title = {Modeling the Interplay Between Emotion and Decision-Making},
author = {Jonathan Gratch},
url = {http://ict.usc.edu/pubs/Modeling%20the%20Interplay%20Between%20Emotion%20and%20Decision-Making.pdf},
year = {2000},
date = {2000-01-01},
booktitle = {Proceedings of the 9th Conference on Computer Generated Forces and Behavioral Representation},
abstract = {Current models of computer-generated forces are limited by their inability to model many of the moderators that influence the performance of real troops in the field such as the effects of stress, emotion, and individual differences. This article discusses an extension to our command and control modeling architecture that begins to address how behavioral moderators influence the command decision-making process. Our Soar-Cfor command architecture was developed under the STOW and ASTT programs to support distributed command and control decision-making in the domain of army aviation planning. We have recently extended this architecture to model how people appraise the emotional significance of events and how these events influence decision making.},
keywords = {Virtual Humans},
pubstate = {published},
tppubtype = {inproceedings}
}
Scholer, Andrew; Rickel, Jeff; Angros, Richard Jr.; Johnson, W. Lewis
Learning Domain Knowledge for Teaching Procedural Tasks Inproceedings
In: AAAI-2000 Fall Symposium on Learning How to Do Things, 2000.
Abstract | Links | BibTeX | Tags:
@inproceedings{scholer_learning_2000,
title = {Learning Domain Knowledge for Teaching Procedural Tasks},
author = {Andrew Scholer and Jeff Rickel and Richard Jr. Angros and W. Lewis Johnson},
url = {http://ict.usc.edu/pubs/Learning%20Domain%20Knowledge%20for%20Teaching%20Procedural%20Tasks.pdf},
year = {2000},
date = {2000-01-01},
booktitle = {AAAI-2000 Fall Symposium on Learning How to Do Things},
abstract = {Providing domain knowledge needed by intelligent tutoring systems to teach a procedure to students is traditionally a difficult and time consuming task. This paper presents a system for making this process easier by allowing the automated tutor to acquire the knowledge it needs through a combination of programming by demonstration, autonomous experimentation, and direct instruction.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Gratch, Jonathan
Socially Situated Planning Incollection
In: Socially Intelligent Agents, Multiagent Systems, Artificial Societies, and Simulated Organizations, vol. 3, pp. 181–188, AAAI Fall Symposium on Socially Intelligent Agents - The Human in the Loop, North Falmouth, MA, 2000.
Abstract | Links | BibTeX | Tags: Virtual Humans
@incollection{gratch_socially_2000,
title = {Socially Situated Planning},
author = {Jonathan Gratch},
url = {http://ict.usc.edu/pubs/Socially%20Situated%20Planning.pdf},
year = {2000},
date = {2000-01-01},
booktitle = {Socially Intelligent Agents, Multiagent Systems, Artificial Societies, and Simulated Organizations},
volume = {3},
pages = {181--188},
address = {AAAI Fall Symposium on Socially Intelligent Agents - The Human in the Loop, North Falmouth, MA},
abstract = {Introduction: Virtual environments such as training simulators and video games do an impressive job at modeling the physical dynamics of synthetic worlds but fall short when modeling the social dynamics of anything but the most impoverished human encounters. Yet the social dimension is at least as important as good graphics for creating an engaging game or effective training tool. Commercial flight simulators accurately model the technical aspects of flight but many aviation disasters arise from social breakdowns: poor management skills in the cockpit, or the effects of stress and emotion. Perhaps the biggest consumer of simulation technology, the U.S. military, identifies unrealistic human and organizational behavior as a major limitation of existing simulation technology (NRC, 1998). And of course the entertainment industry has long recognized the importance of good character, emotional attachment and rich social interactions to "put butts in seats." This article describes a research effort to endow virtual training environments with richer models of social behavior. We have been developing autonomous and semi-autonomous software agents that plan and act while situated in a social network of other entities, human and synthetic (Hill et. al, 1997; Tambe, 1997; Gratch and Hill, 1999). My work has focused on making agents act in an organization and obey social constraints, coordinate their behavior, negotiate conflicts, but also obey their own self-interest and show a range of individual differences in their behavior and willingness to violate social norms, albeit within the relatively narrow context of a specific training exercise.},
keywords = {Virtual Humans},
pubstate = {published},
tppubtype = {incollection}
}
Bharitkar, Sunil; Kyriakakis, Chris
Eigenfilters for Signal Cancellation Inproceedings
In: International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS), Hawaii, 2000.
Abstract | Links | BibTeX | Tags:
@inproceedings{bharitkar_eigenfilters_2000,
title = {Eigenfilters for Signal Cancellation},
author = {Sunil Bharitkar and Chris Kyriakakis},
url = {http://ict.usc.edu/pubs/EIGENFILTERS%20FOR%20SIGNAL%20CANCELLATION.pdf},
year = {2000},
date = {2000-01-01},
booktitle = {International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)},
address = {Hawaii},
abstract = {Selectively canceling signals at specific locations within an acoustical environment with multiple listeners is of significant importance for home theater, automobile, teleconferencing, office, industrial and other applications. The traditional noise cancellation approach is impractical for such applications because it requires sensors that must be placed on the listeners. In this paper we investigate the theoretical properties of eigenfilters for signal cancellation proposed in [1]. We also investigate the sensitivity of the eigenfilter as a function of the room impulse response duration. Our results show that with the minimum phase model for the room impulse response, we obtain a better behaviour in the sensitivity of the filter to the duration of the room response.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Srinivasamurthy, Naveen; Ortega, Antonio; Narayanan, Shrikanth
Efficient Scalable Speech Compression for Scalable Speech Recognition Inproceedings
In: Proceedings of the IEEE Conference on Multimedia and Expo, 2000.
Abstract | Links | BibTeX | Tags:
@inproceedings{srinivasamurthy_efficient_2000,
title = {Efficient Scalable Speech Compression for Scalable Speech Recognition},
author = {Naveen Srinivasamurthy and Antonio Ortega and Shrikanth Narayanan},
url = {http://ict.usc.edu/pubs/Efficient%20Scalable%20Speech%20Compression%20for%20Scalable%20Speech%20Recognition.pdf},
year = {2000},
date = {2000-01-01},
booktitle = {Proceedings of the IEEE Conference on Multimedia and Expo},
abstract = {We propose a scalable recognition system for reducing recognition complexity. Scalable recognition can be combined with scalable compression in a distributed speech recognition (DSR) application to reduce both the computational load and the bandwidth requirement at the server. A low complexity preprocessor is used to eliminate the unlikely classes so that the complex recognizer can use the reduced subset of classes to recognize the unknown utterance. It is shown that by using our system it is fairly straightforward to trade-off reductions in complexity for performance degradation. Results of preliminary experiments using the TI-46 word digit database show that the proposed scalable approach can provide a 40% speed up, while operating under 1.05 kbps, compared to the baseline recognition using uncompressed speech.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
1999
Georgiou, Panayiotis G.; Tsakalides, Panagiotis; Kyriakakis, Chris
Alpha-Stable Modeling of Noise and Robust Time- Delay Estimation in the Presence of Impulsive Noise Inproceedings
In: IEEE Transactions on Multimedia, pp. 291–301, 1999.
Abstract | Links | BibTeX | Tags:
@inproceedings{georgiou_alpha-stable_1999,
title = {Alpha-Stable Modeling of Noise and Robust Time- Delay Estimation in the Presence of Impulsive Noise},
author = {Panayiotis G. Georgiou and Panagiotis Tsakalides and Chris Kyriakakis},
url = {http://ict.usc.edu/pubs/Alpha-Stable%20Modeling%20of%20Noise%20and%20Robust%20Time-%20Delay%20Estimation%20in%20the%20Presence%20of%20Impulsive%20Noise.pdf},
year = {1999},
date = {1999-09-01},
booktitle = {IEEE Transactions on Multimedia},
volume = {1},
pages = {291--301},
abstract = {A new representation of audio noise signals is proposed, based on symmetric-stable (S S) distributions in order to better model the outliers that exist in real signals. This representation addresses a shortcoming of the Gaussian model, namely, the fact that it is not well suited for describing signals with impulsive behavior. The stable and Gaussian methods are used to model measured noise signals. It is demonstrated that the stable distribution, which has heavier tails than the Gaussian distribution, gives a much better approximation to real-world audio signals. The significance of these results is shown by considering the time delay estimation (TDE) problem for source localization in teleimmersion applications. In order to achieve robust sound source localization, a novel time delay estimation approach is proposed. It is based on fractional lower order statistics (FLOS), which mitigate the effects of heavy-tailed noise. An improvement in TDE performance is demonstrated using FLOS that is up to a factor of four better than what can be achieved with second-order statistics.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Gratch, Jonathan; Hill, Randall W.
Continuous Planning and Collaboration for Command and Control in Joint Synthetic Battlespaces Inproceedings
In: Proceedings of the 8th Conference on Computer Generated Forces and Behavioral Representation, Orlando, FL, 1999.
Abstract | Links | BibTeX | Tags: Social Simulation, Virtual Humans
@inproceedings{gratch_continuous_1999,
title = {Continuous Planning and Collaboration for Command and Control in Joint Synthetic Battlespaces},
author = {Jonathan Gratch and Randall W. Hill},
url = {http://ict.usc.edu/pubs/Continuous%20Planning%20and%20Collaboration%20for%20Command%20and%20Control%20in%20Joint%20Synthetic%20Battlespaces.pdf},
year = {1999},
date = {1999-05-01},
booktitle = {Proceedings of the 8th Conference on Computer Generated Forces and Behavioral Representation},
address = {Orlando, FL},
abstract = {In this paper we describe our efforts to model command and control entities for Joint Synthetic Battlespaces. Command agents require a broader repertoire of capabilities than is typically modeled in simulation. They must develop mission plans involving multiple subordinate units, monitor execution, dynamically modify mission plans in response to situational contingencies, collaborate with other decision makers, and deal with a host of organizational issues. We describe our approach to command agent modeling that addresses a number of these issues through its continuous and collaborative approach to mission planning.},
keywords = {Social Simulation, Virtual Humans},
pubstate = {published},
tppubtype = {inproceedings}
}
Gratch, Jonathan; Marsella, Stacy C.; Hill, Randall W.; III, LTC George Stone
Deriving Priority Intelligence Requirements for Synthetic Command Entities Inproceedings
In: Proceedings of the 8th Conference on Computer Generated Forces and Behavioral Representation, Orlando, FL, 1999.
Abstract | Links | BibTeX | Tags: Social Simulation, Virtual Humans
@inproceedings{gratch_deriving_1999,
title = {Deriving Priority Intelligence Requirements for Synthetic Command Entities},
author = {Jonathan Gratch and Stacy C. Marsella and Randall W. Hill and LTC George Stone III},
url = {http://ict.usc.edu/pubs/Deriving%20Priority%20Intelligence%20Requirements%20for%20Synthetic%20Command%20Entities.pdf},
year = {1999},
date = {1999-05-01},
booktitle = {Proceedings of the 8th Conference on Computer Generated Forces and Behavioral Representation},
address = {Orlando, FL},
abstract = {Simulation-based training is using increasingly complex synthetic forces. As more complex multiechelon synthetic forces are employed in simulations, the need for a realistic model of their command and control behavior becomes more urgent. In this paper we discuss one key component of such a model, the autonomous generation and use of priority intelligence requirements within multi-echelon plans.},
keywords = {Social Simulation, Virtual Humans},
pubstate = {published},
tppubtype = {inproceedings}
}
Kyriakakis, Chris; Tsakalides, Panagiotis; Holman, Tomlinson
Surrounded by Sound: Acquisition and Rendering Methods for Immersive Audio Journal Article
In: Signal Processing Magazine, IEEE, vol. 16, no. 1, pp. 55–66, 1999, ISSN: 1053-5888.
Abstract | Links | BibTeX | Tags:
@article{kyriakakis_surrounded_1999,
title = {Surrounded by Sound: Acquisition and Rendering Methods for Immersive Audio},
author = {Chris Kyriakakis and Panagiotis Tsakalides and Tomlinson Holman},
url = {http://ict.usc.edu/pubs/Surrounded%20by%20Sound-%20Acquisition%20and%20Rendering%20Methods%20for%20Immersive%20Audio.pdf},
doi = {10.1109/79.743868},
issn = {1053-5888},
year = {1999},
date = {1999-01-01},
journal = {Signal Processing Magazine, IEEE},
volume = {16},
number = {1},
pages = {55--66},
abstract = {The authors discuss immersive audio systems and the signal processing issues that pertain to the acquisition and subsequent rendering of 3D sound fields over loudspeakers. On the acquisition side, recent advances in statistical methods for achieving acoustical arrays in audio applications are reviewed. Classical array signal processing addresses two major aspects of spatial filtering, namely localization of a signal of interest, and adaptation of the spatial response of an array of sensors to achieve steering in a given direction. The achieved spatial focusing in the direction of interest makes array signal processing a necessary component in immersive sound acquisition systems. On the rendering side, 3D audio signal processing methods are described that allow rendering of virtual sources around the listener using only two loudspeakers. Finally, the authors discuss the commercial implications of audio DSP.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Traum, David; Andersen, Carl F.; Chong, Waiyian; Josyula, Darsana; Okamoto, Yoshi; Purang, Khemdut; O'Donovan-Anderson, Michael; Perlis, Don
Representations of Dialogue State for Domain and Task Independent Meta-Dialogue Journal Article
In: Electronic Transactions on Artificial Intelligence, vol. 3, pp. 125–152, 1999.
Abstract | Links | BibTeX | Tags: Virtual Humans
@article{traum_representations_1999,
title = {Representations of Dialogue State for Domain and Task Independent Meta-Dialogue},
author = {David Traum and Carl F. Andersen and Waiyian Chong and Darsana Josyula and Yoshi Okamoto and Khemdut Purang and Michael O'Donovan-Anderson and Don Perlis},
url = {http://ict.usc.edu/pubs/Representations%20of%20Dialogue%20State%20for%20Domain%20and%20Task%20Independent%20Meta-Dialogue.pdf},
year = {1999},
date = {1999-01-01},
journal = {Electronic Transactions on Artificial Intelligence},
volume = {3},
pages = {125--152},
abstract = {We propose a representation of local dialogue context motivated by the need to react appropriately to meta-dialogue, such as various sorts of corrections to the sequence of an instruction and response action. Such contexts includes at least the following aspects: the words and linguistic structures uttered, the domain correlates of those linguistic structures, and plans and actions in response. Each of these is needed as part of the context in order to be able to correctly interpret the range of possible corrections. Partitioning knowledge of dialogue structure in this way may lead to an ability to represent generic dialogue structure (e.g., in the form of axioms), which can be particularized to the domain, topic and content of the dialogue.},
keywords = {Virtual Humans},
pubstate = {published},
tppubtype = {article}
}
Gratch, Jonathan
Why You Should Buy an Emotional Planner Inproceedings
In: Proceedings of the Agents '99 Workshop on Emotion-Based Agent Architectures, 1999.
Abstract | Links | BibTeX | Tags: Virtual Humans
@inproceedings{gratch_why_1999,
title = {Why You Should Buy an Emotional Planner},
author = {Jonathan Gratch},
url = {http://ict.usc.edu/pubs/Why%20You%20Should%20Buy%20an%20Emotional%20Planner.pdf},
year = {1999},
date = {1999-01-01},
booktitle = {Proceedings of the Agents '99 Workshop on Emotion-Based Agent Architectures},
abstract = {Computation models of emotion have begun to address the problem of how agents arrive at a given emotional state, and how that state might alter their reactions to the environment. Existing work has focused on reactive models of behavior and does not, as of yet, provide much insight on how emotion might relate to the construction and execution of complex plans. This article focuses on this later question. I present a model of how agents ap- praise the emotion significance of events that illustrates a complementary relationship between classical planning methods and models of emotion processing. By building on classical planning methods, the model clarifies prior accounts of emotional appraisal and extends these ac- counts to handle the generation and execution of com- plex multi-agent plans.},
keywords = {Virtual Humans},
pubstate = {published},
tppubtype = {inproceedings}
}
0000
Gratch, Jonathan
Emotion recognition ≠ Emotion Understanding: Challenges Confronting the Field of Affective Computing Journal Article
In: pp. 9, 0000.
BibTeX | Tags: Emotions, Virtual Humans
@article{gratch_emotion_nodate,
title = {Emotion recognition ≠ Emotion Understanding: Challenges Confronting the Field of Affective Computing},
author = {Jonathan Gratch},
pages = {9},
keywords = {Emotions, Virtual Humans},
pubstate = {published},
tppubtype = {article}
}
Gervits, Felix; Leuski, Anton; Bonial, Claire; Gordon, Carla; Traum, David
A Classification-Based Approach to Automating Human-Robot Dialogue Journal Article
In: pp. 13, 0000.
Abstract | Links | BibTeX | Tags: ARL, Dialogue, UARC, Virtual Humans
@article{gervits_classication-based_nodate,
title = {A Classification-Based Approach to Automating Human-Robot Dialogue},
author = {Felix Gervits and Anton Leuski and Claire Bonial and Carla Gordon and David Traum},
url = {https://link.springer.com/chapter/10.1007/978-981-15-9323-9_10},
doi = {https://doi.org/10.1007/978-981-15-9323-9_10},
pages = {13},
abstract = {We present a dialogue system based on statistical classification which was used to automate human-robot dialogue in a collaborative navigation domain. The classifier was trained on a small corpus of multi-floor Wizard-of-Oz dialogue including two wizards: one standing in for dialogue capabilities and another for navigation. Below, we describe the implementation details of the classifier and show how it was used to automate the dialogue wizard. We evaluate our system on several sets of source data from the corpus and find that response accuracy is generally high, even with very limited training data. Another contribution of this work is the novel demonstration of a dialogue manager that uses the classifier to engage in multifloor dialogue with two different human roles. Overall, this approach is useful for enabling spoken dialogue systems to produce robust and accurate responses to natural language input, and for robots that need to interact with humans in a team setting.},
keywords = {ARL, Dialogue, UARC, Virtual Humans},
pubstate = {published},
tppubtype = {article}
}
Hartholt, Arno; McCullough, Kyle; Mozgai, Sharon; Ustun, Volkan; Gordon, Andrew S
Introducing RIDE: Lowering the Barrier of Entry to Simulation and Training through the Rapid Integration & Development Environment Journal Article
In: pp. 11, 0000.
@article{hartholt_introducing_nodate,
title = {Introducing RIDE: Lowering the Barrier of Entry to Simulation and Training through the Rapid Integration & Development Environment},
author = {Arno Hartholt and Kyle McCullough and Sharon Mozgai and Volkan Ustun and Andrew S Gordon},
pages = {11},
abstract = {This paper describes the design, development, and philosophy of the Rapid Integration & Development Environment (RIDE). RIDE is a simulation platform that unites many Department of Defense (DoD) and Army simulation efforts to provide an accelerated development foundation and prototyping sandbox that provides direct benefit to the U.S. Army’s Synthetic Training Environment (STE) as well as the larger DoD and Army simulation communities. RIDE integrates a range of capabilities, including One World Terrain, Non-Player Character AI behaviors, xAPI logging, multiplayer networking, scenario creation, destructibility, machine learning approaches, and multi-platform support. The goal of RIDE is to create a simple, drag-and-drop development environment usable by people across all technical levels. RIDE leverages robust game engine technology while designed to be agnostic to any specific game or simulation engine. It provides decision makers with the tools needed to better define requirements and identify potential solutions in much less time and at much reduced costs. RIDE is available through Government Purpose Rights. We aim for RIDE to lower the barrier of entry to research and development efforts within the simulation community in order to reduce required time and effort for simulation and training prototyping. This paper provides an overview of our objective, overall approach, and next steps, in pursuit of these goals.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Hartholt, Arno; McCullough, Kyle; Mozgai, Sharon; Ustun, Volkan; Gordon, Andrew S
Introducing RIDE: Lowering the Barrier of Entry to Simulation and Training through the Rapid Integration & Development Environment Journal Article
In: pp. 11, 0000.
@article{hartholt_introducing_nodate-1,
title = {Introducing RIDE: Lowering the Barrier of Entry to Simulation and Training through the Rapid Integration & Development Environment},
author = {Arno Hartholt and Kyle McCullough and Sharon Mozgai and Volkan Ustun and Andrew S Gordon},
pages = {11},
abstract = {This paper describes the design, development, and philosophy of the Rapid Integration & Development Environment (RIDE). RIDE is a simulation platform that unites many Department of Defense (DoD) and Army simulation efforts to provide an accelerated development foundation and prototyping sandbox that provides direct benefit to the U.S. Army’s Synthetic Training Environment (STE) as well as the larger DoD and Army simulation communities. RIDE integrates a range of capabilities, including One World Terrain, Non-Player Character AI behaviors, xAPI logging, multiplayer networking, scenario creation, destructibility, machine learning approaches, and multi-platform support. The goal of RIDE is to create a simple, drag-and-drop development environment usable by people across all technical levels. RIDE leverages robust game engine technology while designed to be agnostic to any specific game or simulation engine. It provides decision makers with the tools needed to better define requirements and identify potential solutions in much less time and at much reduced costs. RIDE is available through Government Purpose Rights. We aim for RIDE to lower the barrier of entry to research and development efforts within the simulation community in order to reduce required time and effort for simulation and training prototyping. This paper provides an overview of our objective, overall approach, and next steps, in pursuit of these goals.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Hartholt, Arno; Mozgai, Sharon
From Combat to COVID-19 – Managing the Impact of Trauma Using Virtual Reality Journal Article
In: pp. 35, 0000.
Abstract | BibTeX | Tags: DTIC, MedVR, Virtual Humans, VR
@article{hartholt_combat_nodate,
title = {From Combat to COVID-19 – Managing the Impact of Trauma Using Virtual Reality},
author = {Arno Hartholt and Sharon Mozgai},
pages = {35},
abstract = {Research has documented the efficacy of clinical applications that leverage Virtual Reality (VR) for assessment and treatment purposes across a wide range of domains, including pain, phobias, and posttraumatic stress disorder (PTSD). As the field of Clinical VR matures, it is important to review its origins and examine how these initial explorations have progressed, what gaps remain, and what opportunities the community can pursue. We do this by reflecting on our personal scientific journey against the backdrop of the field in general. In particular, this paper discusses how a clinical research program that was initially designed to deliver trauma-focused VR exposure therapy (VRET) for combat-related PTSD has been evolved to expand its impact and address a wider range of trauma sources. Such trauma sources include sexual trauma and the needs of first responders and healthcare professionals serving on the frontlines of the COVID-19 pandemic. We provide an overview of the field and its general trends, discuss the genesis of our research agenda and its current status, and summarize upcoming opportunities, together with common challenges and lessons learned.},
keywords = {DTIC, MedVR, Virtual Humans, VR},
pubstate = {published},
tppubtype = {article}
}
The Interservice Industry, Training, Simulation, and Education Conference Miscellaneous
0000.
@misc{noauthor_interservice_nodate,
title = {The Interservice Industry, Training, Simulation, and Education Conference},
url = {https://www.xcdsystem.com/iitsec/proceedings/index.cfm?Year=2021&AbID=97189&CID=862},
urldate = {2022-09-22},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
APA PsycNet Miscellaneous
0000.
@misc{noauthor_apa_nodate,
title = {APA PsycNet},
url = {https://psycnet.apa.org/fulltext/2022-19957-001.html},
urldate = {2022-09-13},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}