Select a calendar:
Filter April Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Events for April 01, 2010
-
Dialocalization: Acoustic Speaker Diarization and Visual Localization as Joint Optimization Proble
Thu, Apr 01, 2010 @ 10:00 AM - 11:00 AM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Abstract:
Research in cognitive psychology suggests that the human brain is able to integrate different sensory modalities, such as sight, sound, and touch, into a perceptual experience that is coherent and unified. Experiments show that by considering input from multiple sensors, perceptual problems can be solved more robustly and even more efficiently. In computer science, however, synergistic use of data encoded for different human sensors has not yet lived up to its promise.In the talk, I present a novel multimodal approach for unsupervised speaker localization in both time and space. Using recordings from a single, low-resolution room overview camera and a single far-field microphone, a state-of-the-art audio only speaker diarization system (speaker localization in time) is extended so that both acoustic and visual models are estimated as part of a joint unsupervised optimization problem. The speaker diarization system first automatically determines the speech regions and estimates "who spoke when", then, in a second step, the visual models are used to infer the location of the speakers in the video. We call this process "dialocalization". The proposed system is able to exploit audio-visual integration to not only improve the accuracy of a state-of-the-art (audio-only) speaker diarization, but also adds visual speaker localization at little incremental engineering and computation costs. The combined algorithm has different properties, such as increased robustness, that cannot be observed in algorithms based on single modalities. The talk describes the algorithm, presents benchmarking results, explains its properties, and systematically discusses the contributions of each modality.Bio:
Dr. Gerald Friedland is a research scientist at the International Computer Science Institute (ICSI), a private research lab affiliated with the University of California Berkeley, where he leads the speaker diarization research projects. He is also the Co-PI on an NGA-funded project on Multimodal Location Detection and a member of the Executive Advisory Board of UC Berkeley's Opencast project.Until recently, he was ICSI's site manager in the EU-funded project AMIDA and the Swiss-funded IM2 project, and former co-PI on the DTO-VACE-funded project ROADMAP, all of which explore multimodal signal analysis to interpret people's behavior in meetings and videoconferences. He has published more than 80 peer-reviewed articles in conferences, journals, and books and is currently authoring a new textbook on multimedia computing together with Dr. Ramesh Jain. Dr. Friedland was program co-chair of the IEEE International Symposium on Multimedia 2008 and 2009. He co-founded the IEEE International Conference on Semantic Computing and is a proud founder and program director of the International Summer School on Semantic Computing at UC Berkeley. He is the recipient of several research and industry recognitions, among them the European Academic Software Award and the Multimedia Entrepreneur Award by the German Federal Department of Economics. Most recently, he led the team that won the ACM Multimedia Grand Challenge 2009. Dr. Friedland received his doctorate (summa cum laude) and master's degree in computer science from Freie Universitaet Berlin, Germany, in 2006 and 2002, respectively.Hosts: Professor Shrikanth Narayanan and Dr. Kyu HanLocation: Ronald Tutor Hall of Engineering (RTH) - 320
Audiences: Everyone Is Invited
Contact: Mary Francis
-
Design, Analysis, and Test of Logic Circuits under Uncertainty
Thu, Apr 01, 2010 @ 02:15 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Dr. Smita Krishnaswamy,
IBM, TJ Watson Research CenterAbstract:
Logic circuits are becoming increasingly susceptible to probabilistic behavior caused by external radiation and noise. In addition, inherently probabilistic quantum- and nano-technologies are on the horizon as we approach the limits of CMOS scaling. Ensuring the reliability of such circuits despite the probabilistic behavior is a key challenge in IC design---one that necessitates a fundamental, probabilistic reformulation of synthesis and testing techniques.In this talk, I will present techniques for analyzing, designing, and testing logic circuits with probabilistic behavior. First, I will present a mathematical formulation of reliability analysis using our probabilistic transfer matrix (PTM) algebra for representing probabilistic behavior in gates and circuits. Reliability analysis is a computationally-complex task, and scalability is particularly challenging. To this end, I present two scalable heuristics for approximate analysis in the contexts of testing and reliable design.The first heuristic, involving partial PTM computation, is used to generate tests for probabilistic faults. The second heuristic, known as AnSER, runs in linear time of the size of the circuit, and uses functional-simulation signatures and observability to determine the circuit's soft error rate (SER) accurately. The scalability of AnSER allows us to derive subtle, low-overhead design techniques that improve reliability. These techniques include partial-redundancy identification, guided rewriting, gate relocation, and observability-based retiming. I conclude by briefly covering ongoing research and future directions.Biography:
Smita Krishnaswamy is currently a research staff member in the design automation group at IBM's TJ Watson Research Center, where she works on techniques for incremental design, logic synthesis, and physical synthesis. Her incremental design research has been extensively utilized in production of the P and Z series microprocessor chips.Smita obtained her Ph.D. in computer science and engineering from the University of Michigan, Ann Arbor, in 2008. She has received a 2009 EDAA Outstanding Dissertation Award, and a Best Paper Award at DATE 2005 for her doctoral work. Smita's research interests include fault tolerance, reliability, testing, logic synthesis, and CAD for emerging technologiesHosted by Prof. Sandeep GuptaLocation: Henry Salvatori Computer Science Center (SAL) - -222
Audiences: Everyone Is Invited
Contact: Estela Lopez
