-
Speech and Multimedia Research at ICSI
Mon, Mar 25, 2013 @ 02:00 PM - 03:30 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Roberto Pieraccini, CEO and Director, ICSI
Talk Title: Speech and Multimedia Research at ICSI
Abstract: ICSI, the International Computer Science Institute, is an independent organization affiliated with the University of California at Berkeley. Its mission is that of pursuing advanced computer science research through international collaboration. The Institute is involved in research in many areas, including Networking and Security, Computer Vision, Speech, Audio and Multimedia, Artificial Intelligence, and Computational Biology. In this talk I will give a general overview of the research carried out in the different fields, with particular attention to the areas of speech, audio, and multimedia. Speech research at ICSI is focused on trying to address the limitation of the current speech recognition systems both in terms of modeling and needs for data. Audio and multimedia research is mostly involved in different video retrieval tasks and has shown that interesting results can be achieved by applying a mix of techniques typically used in tasks such as speaker verification and diarization.
Biography: Roberto Pieraccini is the CEO and Director of the International Computer Science Institute (ICSI) in Berkeley, CA. Prior to that he was the Chief Technology Officer of SpeechCycle, a company specializing in advanced spoken human-machine interaction. He was also a research manager at IBM T.J. Watson Research and SpeechWorks International, and a member of the technical staff at Bell Labs and AT&T Shannon Laboratories. He started his career in the 1980s as a researcher at CSELT, the research laboratories of the Italian telephone company. His is the author and co-author of more than 130 publications in the fields of speech recognition, spoken language understanding and dialog, multimodal interaction, and machine learning. His book ââ¬ÅThe Voice in the Machineââ¬Â published by MIT Press in 2012, traces the history of speech recognition and understanding technology during the past 60 years.
Host: Prof. Shrikanth Narayanan
Location: Ronald Tutor Hall of Engineering (RTH) - 320
Audiences: Everyone Is Invited
Contact: Mary Francis