ABSTRACT

The natural language for most deaf signers in the United States is American Sign Language (ASL). ASL has internal structure like spoken languages, and ASL linguists have introduced several phonemic models. The study of ASL phonemes is not only interesting to linguists, but also useful for scalability in recognition by machines. Since machine perception is different than human perception, this paper learns the basic units for ASL directly from data. Comparing with previous studies, our approach computes a set of data-driven units (fenemes) discriminatively from the results of segmental feature selection. The learning iterates the following two steps: first apply discriminative feature selection segmentally to the signs, and then tie the most similar temporal segments to re-train. Intuitively, the sign parts indistinguishable to machines are merged to form basic units, which we call ASL fenemes. Experiments on publicly available ASL recognition data show that the extracted data-driven fenemes are meaningful, and recognition using those fenemes achieves improved accuracy at reduced model complexity

Investigator(s): Umakishore Ramachandran, (Principal Investigator), Irfan Essa (Co-Principal Investigator)

Dates: September 1, 2008 – August 31, 2009 (Estimated)

Abstract

From the western world to the third world, the use of handheld devices (cellphones, PDAs) has proliferated. The world of users is becoming both wireless and mobile. Web 2.0 has ushered in an age wherein the web is viewed as a provider of services and not just a repository of documents and/or information. Despite this advance, the web remains just that, a single web with an inherent assumption that a powerful computing and communication infrastructure supports it. Couldn’t mobile wireless devices in close proximity form a web of their own? This is the vision behind this project, the Web on Demand (WoD). WoD aims at bridging the gap between social networks and ad hoc networking. In other words, it aims to rethink the system software stack all the way from application to networking that would allow the creation and management of social networks without any assumption of infrastructure support. The core of the research is to develop software technologies for mobile devices that would allow the dynamic creation of thematic ad hoc overlay networks empowering (a) mobile people with similar interests (e.g., weather forecast), (b) friends and family (e.g., in a theme park), and (c) participants in mission critical applications (e.g., search and rescue), stay connected. WoD complements the World Wide Web (WWW) and leverages it when it is available, such as exploiting the ambient computing infrastructure to enhance user experience, and managing the dynamic creation of User Generated Content (UGC) by mobile users. The vision behind this project is to democratize access to services that are currently offered through WWW. In this sense, the results from this research can have far-reaching technological and societal consequences. Most importantly, the research will help breed a new class of computer scientists who are connected with societal causes in addition to advancing technology.

ABSTRACT

We address the feature selection problem for hidden Markov models (HMMs) in sequence classification. Temporal correlation in sequences often causes difficulty in applying feature selection techniques. Inspired by segmental k-means segmentation (SKS), we propose Segmentally Boosted HMMs (SBHMMs), where the state-optimized features are constructed in a segmental and discriminative manner. The contributions are twofold. First, we introduce a novel feature selection algorithm, where the temporal dynamics are decoupled from the static learning procedure by assuming that the sequential data are piecewise independent and identically distributed. Second, we show that the SBHMM consistently improves traditional HMM recognition in various domains. The reduction of error compared to traditional HMMs ranges from 17% to 70% in American Sign Language recognition, human gait identification, lip reading, and speech recognition.

ABSTRACT

Fundamentally, journalism is aimed at collecting news information and disseminating that information with a layer of contextualization and understanding provided by journalists. Recent advances in computational technology are rapidly affecting how news information is gathered, reported and distributed. Furthermore, new avenues for aggregating, visualizing, summarizing, consuming, and collaborating on news are increasingly becoming popular and challenging traditional practices of Journalism. Following the success of text search, image and video search questions are now poised to make a bigger impact to journalism and other related fields. Computation and Journalism individually share a deep routed interest in Information, and the value it provides to society. The concept of Information Quality, the measure of the value that the information provides to the user of that information, brings these two disciplines together. In computing and information sciences, information quality is used to describe the degree of excellence in communicating knowledge or intelligence and is composed of different facets such as accuracy, reliability, comprehensiveness, currency, and validity. In journalism, where the conveyance of quality information is paramount, principles such as accuracy, fairness, thoroughness, and transparency guide journalists in communicating quality information. Traditionally, journalism has also entailed an ethos of working on the side of the citizenry to provide them with quality information they need to make informed decisions in the process of their daily lives. However, the plethora of un-vetted blogs, podcasts, videos and other online media, generated by users or by corporations with subjective biases have led to significant compromise in information quality. Collaborative knowledge generation (wikipedia), and citizen journalism, are showing new ways of how information and (global) news can be shared. However, as the Web and the Internet continue to grow and as computing technologies pervade through the planet, a thorough study of the process of journalism and the deep computational aspects of such processes need to be undertaken. To this end, the PI’s research group at Georgia Institute of Technology is interested in understanding how computational advances impact the field of journalism. The long term aim is to make novel contributions by developing computational technologies to better support the goals of journalism. To launch this effort, they are organizing a Symposium on Computation + Journalism at GA Tech, in Atlanta, GA, February 22-23, 2008. The goal of this symposium is to bring together stakeholder from the all aspects of Journalism, Media, and Computation. Participants in panels, presentations and breakout groups will discuss these issues and create a roadmap towards answering these questions that bring together computation and journalism.

Abstract

This thesis examines a large and growing class of digital signals that capture the combined effect of multiple underlying factors. In order to better understand these signals, we would like to separate and analyze the underlying factors independently. Although source separation applies to a wide variety of signals, this thesis focuses on separating individual instruments from a musical recording. In particular, we propose novel algorithms for separating instrument recordings given only their mixture. When the number of source signals does not exceed the number of mixture signals, we focus on a subclass of source separation algorithms based on joint diagonalization. Each approach leverages a different form of source structure. We introduce repetitive structure as an alternative that leverages unique repetition patterns in music and compare its performance against the other techniques.

When the number of source signals exceeds the number of mixtures (i.e., the underdetermined problem), we focus on spectrogram factorization techniques for source separation. We extend single-channel techniques to utilize the additional spatial information in multichannel recordings, and use phase information to improve the estimation of the underlying components.

This project explores the development of methodologies for populating worlds with persistent, adaptive, collaborative, believable synthetic actors, referred to as Synthespians. These methods are extensions of adaptive models of learning and planning to accommodate the complex, dynamic environments in massive multi-player online games. The intellectual merit includes the development and evaluation of: 1. A behavior development language, with discovery, machine learning, and adaptation of behaviors directly integrated into the language, allowing for the rapid development and deployment of Synthespians. 2. A framework for the actors to recognize and discover plans by observing and modeling the activities of the other agents. An expected outcome of this research is the ability to author complex virtual worlds with many participants that support intelligent and effective interaction between people and machines. Broader Impact: A scientific understanding of how we interact with each other and collaborate will benefit from our ability to simulate complex environments with dynamic and evolving individual and group behaviors. In this project, building and modeling such environments and behaviors is done within a gaming context. This work will in the long run effect and change the fields of education and entertainment. In addition, being able to model large collaborative and interactive scenarios will also help us understand and model large social dynamics phenomenon of interest to sociologists and economists.

Abstract

Spectrogram factorization methods have been proposed for single channel source separation and audio analysis. Typically, the mixture signal is first converted into a time-frequency representation such as the short-time Fourier transform (STFT). The phase information is thrown away and this spectrogram matrix is then factored into the sum of rank-one source spectrograms. This approach incorrectly assumes the mixture spectrogram is the sum of the source spectrograms. In fact, the mixture spectrogram depends on the phase of the source STFTs. We investigate the consequences of this common assumption and introduce an approach that leverages a probabilistic representation of phase to improve the separation results

Abstract

We explore optimization strategies and resulting performance of two stream-based video applications, video texture and color tracker, on a cluster of SMPs. The two applications are representative of a class of emerging applications, which we call “stream-based applications”, that are sensitive to both latency of individual results and overall throughput. Such applications require non-trivial parallelization techniques in order to improve both latency and throughput, given that the stream data emanates from a limited set of sources (exactly one in the two applications studied) and that the distribution of the data cannot be done a priori.We suggest techniques that address in a coordinated fashion the problems of data distribution and work partitioning. We believe the two problems are related and need to be addressed together. We have parallelized two applications using the Stampede cluster programming system that provides abstractions for implementing time-and throughput-sensitive applications elegantly and efficiently. For the Video Textures application we show that we can achieve a speedup of 24.26 on a 112 processor cluster. For the Color Tracker application, where latency is more crucial, we identify the extent of data parallelism that ensures that the slowest member of the pipeline is no longer the bottleneck for achieving a decent frame rate.

Abstract

Blind source separation algorithms typically require that the number of sources are known in advance. However, it is often the case that the number of sources change over time and that the total number is not known. Existing source separation techniques require source number estimation methods to determine how many sources are active within the mixture signals. These methods typically operate on the covariance matrix of mixture recordings and require fewer active sources than mixtures. When sources do not overlap in the time-frequency domain, more sources than mixtures may be detected and then separated. However, separating more sources than mixtures when sources overlap in time and frequency poses a particularly difficult problem. This paper addresses the issue of source detection when more sources than sensors overlap in time and frequency. We show that repetitive structure in the form of time-time correlation matrices can reveal when each source is active

Abstract

Speech reading, also known as lip reading, is aimed at extracting visual cues of lip and facial movements to aid in recognition of speech. The main hurdle for speech reading is that visual measurements of lip and facial motion lack information-rich features like the Mel frequency cepstral coefficients (MFCC), widely used in acoustic speech recognition. These MFCC are used with hidden Markov models (HMM) in most speech recognition systems at present. Speech reading could greatly benefit from automatic selection and formation of informative features from measurements in the visual domain. These new features can then be used with HMM to capture the dynamics of lip movement and eventual recognition of lip shapes. Towards this end, we use AdaBoost methods for automatic visual feature formation. Specifically, we design an asymmetric variant of AdaBoost M2 algorithm to deal with the ill-posed multi-class sample distribution inherent in our problem. Our experiments show that the boosted HMM approach outperforms conventional AdaBoost and HMM classifiers. Our primary contributions are in the design of (a) boosted HMM and (b) asymmetric multi-class boosting.

ABSTRACT

We propose to develop a comprehensive framework for the joint analysis of audio-visual signals obtained from spatially distributed microphones and cameras. We desire solutions to the audio-visual sensing problem that will scale to an arbitrary number of cameras and microphones and can address challenging environments in which there are multiple speech and nonspeech sound sources and multiple moving people and objects. Recently it has become relatively inexpensive to deploy tens or even hundreds of cameras and microphones in an environment. Many applications could benefit from ability to sense in both modalities. There are two levels at which joint audio-visual analysis can take place. At the signal level, the challenge is to develop representations that capture the rich dependency structure in the joint signal and deal success-fully issues such as variable sampling rates and varying temporal delays between cues. At the spatial level the challenge is to compensate for the distortions introduced by the sensor location and pool information across sensors to recover 3-D information about the spatial environment. For many applications, it is highly desirable if the solution method is self-calibrating, and does not require an extensive manual calibration process every time a new sensor is added or an old sensor is moved or replaced. Removing the burden of manual calibration also makes it possible to exploit ad hoc sensor networks which could arise, for example, from wearable microphones and cameras. We propose to address the following four research topics: 1. Representations and learning methods for signal level fusion. 2. Volumetric techniques for fusing spatially distributed audio-visual data. 3. Self-calibration of distributed microphone-camera systems 4. Applications of audio-visual sensing. For example, this proposal includes considerable work on lip and facial analysis to improve voice communications.

ABSTRACT

The focus of this project is on development of a domestic environment that is cognizant of the whereabouts and activities of its occupants and can support them in their everyday life. While the technology is applicable to a range of domestic situations, the emphasis in this work will be on support for aging in place; through collaboration with experts in assistive care and cognitive aging, the PI and his team will design, demonstrate, and evaluate a series of domestic services that aim to maintain the quality of life for an aging population, with the goal of increasing the likelihood of a “stay at home” alternative to assisted living that satisfies the needs of an aging individual and his/her distributed family. In particular, the PI will explore two areas that are key to sustaining quality of life for an independent senior adult: maintaining familial vigilance, and supporting daily routines. The intention is to serve as an active partner, aiding the senior occupant without taking control. This research will lead to advances in three research areas: human-computer interaction; computational perception; and software engineering. To achieve the desired goals, the PI will conduct the research and experimentation in an authentic domestic setting, a novel research facility called the Residential Laboratory recently completed next to the Georgia Tech campus. Together with experts in theoretical and practical aspects of aging, the PI will establish a pattern of research in which informed design of ubiquitous computing technology can be rapidly deployed, evaluated and evolved in an authentic setting. Special attention will be paid throughout to issues relating to privacy and trust implications. The PI will transition the products of this project to researchers and practitioners interested in performing more large-scale observations of the social and economic impact of Aware Home technologies.