Publications

@inproceedings{gratch_tears_2001,

title = {Tears and Fears: Modeling emotions and emotional behaviors in synthetic agents},

author = {Jonathan Gratch and Stacy C. Marsella},

url = {http://ict.usc.edu/pubs/Tears%20and%20Fears-%20Modeling%20emotions%20and%20emotional%20behaviors%20in%20synthetic%20agents.pdf},

year  = {2001},

date = {2001-01-01},

booktitle = {Proceedings of the 5th International Conference on Autonomous Agents},

pages = {278–285},

address = {Montreal, Canada},

abstract = {Emotions play a critical role in creating engaging and believable characters to populate virtual worlds. Our goal is to create general computational models to support characters that act in virtual environments, make decisions, but whose behavior also suggests an underlying emotional current. In service of this goal, we integrate two complementary approaches to emotional modeling into a single unified system. Gratch's Émile system focuses on the problem of emotional appraisal: how emotions arise from an evaluation of how environmental events relate to an agent's plans and goals. Marsella et al. 's IPD system focuses more on the impact of emotions on behavior, including the impact on the physical expressions of emotional state through suitable choice of gestures and body language. This integrated model is layered atop Steve, a pedagogical agent architecture, and exercised within the context of the Mission Rehearsal Exercise, a prototype system designed to teach decision- making skills in highly evocative situations.},

keywords = {Social Simulation, Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{hawkins_photometric_2001,

title = {A Photometric Approach to Digitizing Cultural Artifacts},

author = {Tim Hawkins and Jonathan Cohen and Paul Debevec},

url = {http://ict.usc.edu/pubs/A%20Photometric%20Approach%20to%20Digitizing%20Cultural%20Artifacts.pdf},

year  = {2001},

date = {2001-01-01},

booktitle = {Proceedings of 2nd International Symposium on Virtual Reality, Archaeology and Cultural Heritage},

address = {Glyfada, Greece},

abstract = {In this paper we present a photometry-based approach to the digital documentation of cultural artifacts. Rather than representing an artifact as a geometric model with spatially varying reflectance properties, we instead propose directly representing the artifact in terms of its reflectance field - the manner in which it transforms light into images. The principal device employed in our technique is a computer-controlled lighting apparatus which quickly illuminates an artifact from an exhaustive set of incident illumination directions and a set of digital video cameras which record the artifact's appearance under these forms of illumination. From this database of recorded images, we compute linear combinations of the captured images to synthetically illuminate the object under arbitrary forms of complex incident illumination, correctly capturing the effects of specular reflection, subsurface scattering, self-shadowing, mutual illumination, and complex BRDF's often present in cultural artifacts. We also describe a computer application that allows users to realistically and interactively relight digitized artifacts.},

keywords = {Graphics},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{lee_recognition_2001,

title = {Recognition of Negative Emotions from the Speech Signal},

author = {C. M. Lee and Shrikanth Narayanan and R. Pieraccin},

url = {http://ict.usc.edu/pubs/Recognition%20of%20Negative%20Emotions%20from%20the%20Speech%20Signal.pdf},

year  = {2001},

date = {2001-01-01},

booktitle = {Proceedings of Automatic Speech Recognition and Understanding Workshop (ASRU 2001)},

abstract = {This paper reports on methods for automatic classification of spoken utterances based on the emotional state of the speaker. The data set used for the analysis comes from a corpus of human- machine dialogs recorded from a commercial application deployed by SpeechWorks. Linear discriminant classification with Gaussian class-conditional probability distribution and knearest neighborhood methods are used to classify utterances into two basic emotion states, negative and non-negative. The features used by the classifiers are utterance-level statistics of the fundamental frequency and energy of the speech signal. To improve classification performance, two specific feature selection methods are used; namely, promising first selection and forward feature selection. Principal component analysis is used to reduce the dimensionality of the features while maximizing classification accuracy. Improvements obtained by feature selection and PCA are reported in this paper. We reported the results.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{hawkins_light_2001,

title = {Light Stage 2.0},

author = {Tim Hawkins and Jonathan Cohen and Chris Tchou and Paul Debevec},

url = {http://ict.usc.edu/pubs/Light%20Stage%202.pdf},

year  = {2001},

date = {2001-01-01},

booktitle = {SIGGRAPH Technical Sketches},

pages = {217},

keywords = {Graphics},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{olsen_implicit_2001,

title = {Implicit Cues for Explicit Generation: Using Telicity as a Cue for Tense Structure in Chinese to English MT System},

author = {Mari Olsen and David Traum and Carol Van Ess-Dykema and Amy Weinberg},

url = {http://ict.usc.edu/pubs/Implicit%20Cues%20for%20Explicit%20Generation-%20Using%20Telicity%20as%20a%20Cue%20for%20Tense%20Structure%20in%20Chinese%20to%20English%20MT%20System.pdf},

year  = {2001},

date = {2001-01-01},

booktitle = {Machine Translation Summit VIII},

address = {Santiago de Compostela, Spain},

abstract = {In translating from Chinese to English, tense and other temporal information must be inferred from other grammatical and lexical cues. Tense information is crucial to providing accurate and fluent translations into English. Perfective and imperfective grammatical aspect markers can provide cues to temporal structure, but such information is optional in Chinese and is not present in the majority of sentences. We report on a project that assesses the relative contribution of the lexical aspect features of (a)telicity reflected in the Lexical Conceptual Structure of the input text, versus more overt aspectual and adverbial markers of tense, to suggest tense structure in the English translation of a Chinese newspaper corpus. Incorporating this information allows a 20% to 35% boost in the accuracy of tense relization with the best accuracy rate of 92% on a corpus of Chinese articles.},

keywords = {Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{yang_embedded_2001,

title = {Embedded High-Quality Multichannel Audio Coding},

author = {Dai Yang and Hongmei Ai and Chris Kyriakakis and C. -C. Jay Kuo},

url = {http://ict.usc.edu/pubs/Embedded%20High-Quality%20Multichannel%20Audio%20Coding.pdf},

year  = {2001},

date = {2001-01-01},

booktitle = {Conference on Media Processors, Symposium on Electronic Imaging},

address = {San Jose, CA},

abstract = {An embedded high-quality multi-channel audio coding algorithms is proposed in this research. The Karhunen-Loeve Transform (KLT) is applied to multichannel audio signals in the pre-processing stage to remove inter-channel redundancy. Then, after processing of several audio coding blocks, transformed coefficients are layered quantized and the bit stream is ordered according to their importance. The multichannel audio bit stream generated by the propoesed algorithm has a fully progressive property, which is highly desirable for audio multicast applications in heterogenous networks. Experimental results show that, compared with the MPEG Advanced Audio Coding (AAC) algorithm, the proposed algorithm achieves a better performance with both the objective MNR (Mask-to-Noise-Ratio) measurement and the subjective listening test at several different bit rates.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{waese_real_2001,

title = {A Real Time High Dynamic Range Light Probe},

author = {Jamie Waese and Paul Debevec},

url = {http://ict.usc.edu/pubs/A%20Real%20Time%20High%20Dynamic%20Range%20Light%20Probe.pdf},

year  = {2001},

date = {2001-01-01},

booktitle = {SIGGRAPH Technical Sketches},

keywords = {Graphics},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{bharitkar_cluster_2001,

title = {A Cluster Centroid Method for Room Response Equalization at Multiple Locations},

author = {Sunil Bharitkar and Chris Kyriakakis},

url = {http://ict.usc.edu/pubs/A%20CLUSTER%20CENTROID%20METHOD%20FOR%20ROOM%20RESPONSE%20EQUALIZATION%20AT%20MULTIPLE%20LOCATIONS.pdf},

isbn = {0-7803-7126-7},

year  = {2001},

date = {2001-01-01},

booktitle = {IEEE Workshop on the Applications of Signal Processing to Audio and Acoustics},

pages = {55–58},

address = {New Platz, NY},

abstract = {In this paper we address the problem of simultaneous room response equalization for multiple listeners. Traditional approaches to this problem have used a single microphone at the listening position to measure impulse responses from a loudspeaker and then use an inverse filter to correct the frequency response. The problem with that approach is that it only works well for that one point and in most cases is not practical even for one listener with a typical ear spacing of 18 cm. It does not work at all for other listeners in the room, or if the listener changes positions even slightly. We propose a new approach that is based on the Fuzzy c-means clustering technique. We use this method to design equalization filters and demonstrate that we can achieve better equalization performance for several locations in the room simultaneously as compared to single point or simple averaging methods.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{srinivasamurthy_use_2001,

title = {Use of Model Transformations for Distributed Speech Recognition},

author = {Naveen Srinivasamurthy and Shrikanth Narayanan and Antonio Ortega},

url = {http://ict.usc.edu/pubs/Use%20of%20Model%20Transformations%20for%20Distributed%20Speech%20Recognition.pdf},

year  = {2001},

date = {2001-01-01},

booktitle = {4th ISCA Tutorial and Research Workshop on Speech Synthesis},

pages = {113–116},

address = {Sophia Antipolis, France},

abstract = {Due to bandwidth limitations, the speech recognizer in distributed speech recognition (DSR) applications has to use encoded speech - either traditional speech encoding or speech encoding optimized for recognition. The penalty incurred in reducing the bitrate is degradation in speech recognition performance. The diversity of the applications using DSR implies that a variety of speech encoders can be used to compress speech. By treating the encoder variability as a mismatch we propose using model transformation to reduce the speech recognition performance degradation. The advantage of using model transformation is that only a single model set needs to be trained at the server, which can be adapted on the fly to the input speech data. We were able to reduce the word error rate by 61.9%, 63.3% and 56.3% for MELP, GSM and MFCC-encoded data, respectively, by using MAP adaptation, which shows the generality of our proposed scheme.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{damiano_anticipatory_2001,

title = {Anticipatory planning for decision-theoretic grounding and task advancement in mixed-initiative dialogue systems},

author = {Rossana Damiano and David Traum},

url = {http://ict.usc.edu/pubs/Anticipatory%20planning%20for%20decision-theoretic%20grounding%20and%20task%20advancement%20in%20mixed-initiative%20dialogue%20systems.pdf},

year  = {2001},

date = {2001-01-01},

booktitle = {NAACL 2001 Workshop on Adaptation in Dialogue Systems},

keywords = {Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{marsella_modeling_2001,

title = {Modeling the Interplay of Emotions and Plans in Multi-Agent Simulations},

author = {Stacy C. Marsella and Jonathan Gratch},

url = {http://ict.usc.edu/pubs/Modeling%20the%20Interplay%20of%20Emotions%20and%20Plans%20in%20Multi-Agent%20Simulations.pdf},

year  = {2001},

date = {2001-01-01},

booktitle = {Proceedings of 23rd Annual Conference of the Cognitive Science Society},

address = {Edinburgh, Scotland},

abstract = {The goal of this research is to create general computational models of the interplay between affect, cognition and behavior. These models are being designed to support characters that act in virtual environments, make decisions, but whose behavior also suggests an underlying emotional current. We attempt to capture both the cognitive and behavioral aspects of emotion, circumscribed to the role emotions play in the performance of concrete physical tasks. We address how emotions arise from an evaluation of the relationship between environmental events and an agent's plans and goals, as well as the impact of emotions on behavior, in particular the impact on the physical expressions of emotional state through suitable choice of gestures and body language. The approach is illustrated within a virtual reality training environment.},

keywords = {Social Simulation, Virtual Humans},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{yang_adaptive_2001,

title = {Adaptive Karhunen-Loeve Transform for Enhanced Multichannel Audio Coding},

author = {Dai Yang and Hongmei Ai and Chris Kyriakakis and C. -C. Jay Kuo},

url = {http://ict.usc.edu/pubs/Adaptive%20Karhunen-Loeve%20Transform%20for%20Enhanced%20Multichannel%20Audio%20Coding.pdf},

year  = {2001},

date = {2001-01-01},

booktitle = {SPIE},

address = {San Diego, CA},

abstract = {A modified MPEG Advanced Audio Coding (AAC) scheme based on the Karhunen-Loeve transform (KLT) to remove inter-channel redundancy, which is called the MAACKL method, has been proposed in our previous work. However, a straightforward coding of elements of the KLT matrix generates about 240 bits per matrix for typical 5 channel audio contents. Such an overhead is too expensive so that it prevents MAACKL from updating KLT dynamically in a short period of time. In this research, we study the de-correlation efficiency of adaptive KLT as well as an efficient way to encode elements of the KLT matrix via vector quantization. The effect due to different quantization accuracy and adaptation period is examined carefully. It is demonstrated that with the smallest possible number of bits per matrix and a moderately long KLT adaptation time, the MAACKL algorithm can still generate a very good coding performance.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{debevec_acquiring_2000,

title = {Acquiring the Reflectance Field of a Human Face},

author = {Paul Debevec and Tim Hawkins and Chris Tchou and Haarm-Pieter Duiker and Westley Sarokin},

url = {http://ict.usc.edu/pubs/Acquiring%20the%20Re%EF%AC%82ectance%20Field%20of%20a%20Human%20Face.pdf},

year  = {2000},

date = {2000-07-01},

booktitle = {SIGGRAPH},

address = {New Orleans, LA},

abstract = {We present a method to acquire the reflectance field of a human face and use these measurements to render the face under arbitrary changes in lighting and viewpoint. We first acquire images of the face from a small set of viewpoints under a dense sampling of incident illumination directions using a light stage. We then construct a reflectance function image for each observed image pixel from its values over the space of illumination directions. From the reflectance functions, we can directly generate images of the face from the original viewpoints in any form of sampled or computed illumination. To change the viewpoint, we use a model of skin reflectance to estimate the appearance of the reflectance functions for novel viewpoints. We demonstrate the technique with synthetic renderings of a person's face under novel illumination and viewpoints.},

keywords = {Graphics},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{bharitkar_selective_2000,

title = {Selective Signal Cancellation for Multiple Listener Audio Applications: An Information Theory Approach},

author = {Sunil Bharitkar and Chris Kyriakakis},

url = {http://ict.usc.edu/pubs/SELECTIVE%20SIGNAL%20CANCELLATION%20FOR%20MULTIPLE-LISTENER%20AUDIO%20APPLICATIONS-%20AN%20INFORMATION%20THEORY%20APPROACH.pdf},

year  = {2000},

date = {2000-07-01},

booktitle = {IEEE International Conference Multimedia and Expo},

address = {New York, NY},

abstract = {Selectively canceling signals at specific locations within an acoustical environment with multiple listeners is of significant importance for home theater, 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 propose an alternative method to minimize signal power in a given location and maximize signal power in another location of interest. A key advantage of this approach would be the need to eliminate sensors. We investigate the use of an information theoretic criterion known as mutual information to design filter coefficients that selectively cancel a signal in one audio channel, and transmit it in another (complementary) channel. Our results show an improvement in power gain at one location in the room relative to the other.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@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}

}

@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}

}

@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}

}

@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}

}

@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}

}

@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}

}

@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}

}

@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}

}

@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}

}

@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}

}

@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}

}

@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}

}

@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}

}

@inproceedings{chen_dont_nodate,

title = {Don't Look into the Dark: Latent Codes for Pluralistic Image Inpainting},

author = {Haiwei Chen and Yajie Zhao},

url = {https://openaccess.thecvf.com/content/CVPR2024/html/Chen_Dont_Look_into_the_Dark_Latent_Codes_for_Pluralistic_Image_CVPR_2024_paper.html},

pages = {7591–7600},

abstract = {We present a method for large-mask pluralistic image inpainting based on the generative framework of discrete latent codes. Our method learns latent priors discretized as tokens by only performing computations at the visible locations of the image. This is realized by a restrictive partial encoder that predicts the token label for each visible block a bidirectional transformer that infers the missing labels by only looking at these tokens and a dedicated synthesis network that couples the tokens with the partial image priors to generate coherent and pluralistic complete image even under extreme mask settings. Experiments on public benchmarks validate our design choices as the proposed method outperforms strong baselines in both visual quality and diversity metrics.},

keywords = {DTIC, Graphics, VGL},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{artstein_augmenting_nodate,

title = {Augmenting Training Data for a Virtual Character Using GPT-3.5},

author = {Ron Artstein and Elizabeth Chen},

url = {https://journals.flvc.org/FLAIRS/article/view/135552},

volume = {37},

publisher = {Tyhe Florida Artificial Intelligence Research Society},

abstract = {This paper compares different methods of using a large lan-guage model (GPT-3.5) for creating synthetic training datafor a retrieval-based conversational character. The trainingdata are in the form of linked questions and answers, whichallow a classifier to retrieve a pre-recorded answer to an un-seen question; the intuition is that a large language modelcould predict what human users might ask, thus saving theeffort of collecting real user questions as training data. Re-sults show small improvements in test performance for allsynthetic datasets. However, a classifier trained on only smallamounts of collected user data resulted in a higher F-scorethan the classifiers trained on much larger amounts of syn-thetic data generated using GPT-3.5. Based on these results,we see a potential in using large language models for gener-ating training data, but at this point it is not as valuable ascollecting actual user data for training.},

keywords = {Dialogue, DTIC, Natural Language},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{mozgai_persuasive_nodate,

title = {Persuasive Technology for Suicide Prevention: A Virtual Human mHealth Application},

author = {Sharon Mozgai and Albert A Rizzo and Arno Hartholt},

abstract = {We	are	demoing	Battle	Buddy,	an	mHealth	application	designed	to	support	access	to	physical	and	mental	wellness	content	as	well	as	safety	planning	for	U.S.	military	veterans.	This	virtual	human	interface	will	collect	multimodal	data	through	passive	sensors	native	to	popular	wearables	(e.g.,	Apple	Watch)	and	deliver	adaptive	multimedia	content	specifically	tailored	to	the	user	in	the	interdependent	domains	of	physical,	cognitive,	and	emotional	health.	Battle	Buddy	can	deliver	health	interventions	matched	to	the	individual	user	via	novel	adaptive	logic-based	algorithms	while	employing	various	behavior	change	techniques	(e.g.,	goal-setting,	barrier	identification,	rewards,	modeling,	etc.).	All	interactions	were	specifically	designed	to	engage	and	motivate	by	employing	the	persuasive	strategies	of	(1)	personalization,	(2)	self-monitoring,	(3)	tunneling,	(4)	suggestion,	and	(5)	expertise.},

keywords = {Virtual Humans, VR},

pubstate = {published},

tppubtype = {inproceedings}

}