University of Birmingham > Talks@bham > Speech Recognition by Synthesis Seminars > Applications of multitask learning in speech recognition and synthesis

Applications of multitask learning in speech recognition and synthesis

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

  • UserDr. Peter Bell, The Centre for Speech Technology Research, The University of Edinburgh
  • ClockWednesday 18 February 2015, 14:00-15:00
  • HouseGisbert Kapp, N123.

If you have a question about this talk, please contact Dr. Philip Weber.

Multitask learning (Caruana, 1997) has been found to be an effective method of improving the generalisation performance of classifiers. The recent growth in the use of deep neural network models for speech processing enables multitask learning to be integrated easily into the acoustic model training procedure. In this talk I will discuss practical implementations of multitask learning and present recent work where we have applied the technique to range of problem settings in speech recognition and synthesis.

This talk is part of the Speech Recognition by Synthesis Seminars series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

Talks@bham, University of Birmingham. Contact Us | Help and Documentation | Privacy and Publicity.
talks@bham is based on talks.cam from the University of Cambridge.