University of Cambridge > Talks.cam > CUED Speech Group Seminars > Robust speech processing on multi-talker mixed speech

Robust speech processing on multi-talker mixed speech

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Yu Wang.

Although the performance of speech processing systems has surpassed the threshold for adoption for many real-world applications, e.g. speech recognition, speaker recognition, and speech enhancement, etc., there are still difficulties to be solved to make intelligent speech technologies 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 such problem. The cocktail party problem has been wideyl observed. Solving it could enable many scenarios and applications, such as meeting transcription, multi-party human–machine interaction, and hearing impairment assistants, where overlapped speech cannot be ignored. In this talk we will first briefly review the techniques proposed in the last two decades in attacking this problem. Then we will present techniques, which are developed 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-talker 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 given on some benchmark tasks.

This talk is part of the CUED Speech Group Seminars series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2019 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity