BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Robust speech processing on multi-talker mixed speech - Yanmin Qia
 n\, Shanghai Jiao Tong University
DTSTART:20190510T100000Z
DTEND:20190510T110000Z
UID:TALK124333@talks.cam.ac.uk
CONTACT:Yu Wang
DESCRIPTION:Although the performance of speech processing systems has surp
 assed the threshold for adoption for many real-world applications\, e.g. s
 peech recognition\, speaker recognition\, and speech enhancement\, etc.\, 
 there are still difficulties to be solved to make intelligent speech techn
 ologies more widely deployed. The cocktail party problem\, i.e.\, tracing 
 and recognizing the speech from a specific speaker when multiple speakers 
 talk simultaneously and when other background noise is involved\, is one s
 uch problem. The cocktail party problem has been wideyl observed. Solving 
 it could enable many scenarios and applications\, such as meeting transcri
 ption\, multi-party human–machine interaction\, and hearing impairment a
 ssistants\, where overlapped speech cannot be ignored. In this talk we wil
 l first briefly review the techniques proposed in the last two decades in 
 attacking this problem. Then we will present techniques\, which are develo
 ped in SJTU SpeechLab during the recent years\, to improve the performance
  of speech processing system in the cocktail party environment. Two tasks 
 are mainly focused\, including multi-talker speech separation and multi-ta
 lker speech recognition. The newly proposed approaches significantly boost
  the separation quality and recognition accuracy on the multi-talker mixed
  speech processing. Detailed comparison and promising results will be give
 n on some benchmark tasks.
LOCATION:Department of Engineering - James Dyson Building Seminar Room
END:VEVENT
END:VCALENDAR