University of Birmingham > Talks@bham > Speech Recognition by Synthesis Seminars > A Study into Cross Channel Effects on Speaker Verification systems

A Study into Cross Channel Effects on Speaker Verification systems

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

  • UserKeith Jellyman, University of Birmingham
  • ClockWednesday 29 April 2015, 14:00-15:00
  • HouseGisbert Kapp, N123.

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

Significant advancements have been made in automatic speaker verification systems during the last decade and a half. Current state-of-the-art systems are now capable of and required to process millions of trials in academic evaluations. However despite these major advancements the technology is still susceptible to cross channel effects.

The term channel effects is used to refer to variabilities not introduced by the speaker. Some example variabilities include differences between the recording sources, such as interview or telephone, the type of coding used, presence of any background noise and reverberation. In this talk I will present an overview on the state-of-the-art, directions on where I see the technology heading, and outline my research plans.

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.