BEGIN:VCALENDAR
PRODID:-//eluceo/ical//2.0/EN
VERSION:2.0
CALSCALE:GREGORIAN
BEGIN:VEVENT
UID:www.tcs.tifr.res.in/event/47
DTSTAMP:20230914T125908Z
SUMMARY:New Directions in Automated Speech Technologies
DESCRIPTION:Speaker: Richard Stern\nDepartment of Electrical and Comp. Engg
 . and\nLanguage Technologies Institute\nCarnegie Mellon Univers\n\nAbstrac
 t: \nSpeech processing is one of the most important enabling technologies 
 that underly the development of fluent human-machine interfaces. Carnegie 
 Mellon University (CMU) has been a long-term leader in the development of 
 unlimited-vocabulary speech recognition and in spoken language systems\, a
 nd the CMU speech group has developed a broad range of speech processing t
 echnologies including robust speech recognition\, text-to-speech synthesis
 \, speaker identification and verification\, and a broad range of applicat
 ions based on speech processing. While the capabilities of automatic speec
 h recognition systems have improved dramatically over the past decade\, co
 mmercially-successful speech-based applications that exploit these technol
 ogies are still appearing relatively slowly.  Some of the factors that hav
 e limited the deployment of speech-based applications include lack of acou
 stical robustness\,  difficulty in handling out-of-vocabulary words and co
 ncepts\, and difficulty in  automating the process of semantic interpretat
 ion for new domains. This talk will provide a review and discussion of the
  current state-of-the art of speech recognition technology\, including exa
 mples of recent work by the CMU speech group in a variety of application a
 reas.  We describe and demonstrate these applications\, and we discuss som
 e of the significant new problems that have been encountered in transferri
 ng core speech technology to practical applications.\n\nBiodata: Richard M
 . Stern received the S.B. degree from the Massachusetts Institute of Techn
 ology in 1970\, the M.S. from the University of California\, Berkeley\, in
  1972\, and the Ph.D. from MIT in 1977\, all in electrical engineering.   
 He has been on the faculty of Carnegie Mellon University since 1977\, wher
 e he is currently a Professor in the Electrical and Computer Engineering\,
  Computer Science\, and Biomedical Engineering Departments\, the Language 
 Technologies Institute\, and the School of Music.  Much of Dr. Stern's cur
 rent research is in spoken language systems\, where he is particularly con
 cerned with the development of techniques with which automatic speech reco
 gnition can be made more robust with respect to changes in environment and
  acoustical ambience.  He has also developed sentence parsing and speaker 
 adaptation algorithms for earlier CMU speech systems.  In addition to his 
 work in speech recognition\, Dr. Stern has worked extensively in psychoaco
 ustics\, where he is best known for theoretical work in binaural perceptio
 n.  Dr. Stern is a Fellow of the Acoustical Society of America\, the 2008-
 2009 Distinguished Lecturer of the International Speech Communication Asso
 ciation\, a recipient of the Allen Newell Award for Research Excellence in
  1992\, and he served as General Chair of Interspeech 2006.  He is also a 
 member of the IEEE and the Audio Engineering Society.\n
URL:https://www.tcs.tifr.res.in/web/events/47
DTSTART;VALUE=DATE:20091207
LOCATION:AG-80
END:VEVENT
END:VCALENDAR