SuperLectures.com

CLASSIFIER SUBSET SELECTION AND FUSION FOR SPEAKER VERIFICATION

Speaker Verification

Full Paper at IEEE Xplore

Presented by: Filip Sedlak, Author(s): Filip Sedlak, Tomi Kinnunen, University of Eastern Finland, Finland; Ville Hautamäki, Kong Aik Lee, Haizhou Li, Institute for Infocomm Research, Singapore

State-of-the-art speaker verification systems consists of a number of complementary subsystems whose outputs are fused, to arrive at more accurate and reliable verification decision. In speaker verification, fusion is typically implemented as a linear combination of the subsystem scores. Parameters of the linear model are commonly estimated using the logistic regression method, as implemented in the popular FoCal toolkit. In this paper, we study simultaneous use of classifier selection and fusion. We study four alternative fusion strategies, three score warping techniques, and provide interesting experimental bounds on optimal classifier subset selection. Detailed experiments are carried out on the NIST 2008 and 2010 SRE corpora.


  Speech Transcript

|

  Slides

Enlarge the slide | Show all slides in a pop-up window

0:00:16

  1. slide

0:00:27

  2. slide

0:01:32

  3. slide

0:01:59

  4. slide

0:04:09

  5. slide

0:04:45

  6. slide

0:05:31

  7. slide

0:07:26

  8. slide

0:08:43

  9. slide

0:10:26

 10. slide

0:10:54

 11. slide

0:11:48

 12. slide

  Comments

Please sign in to post your comment!

  Lecture Information

Recorded: 2011-05-26 10:10 - 10:30, Panorama
Added: 15. 6. 2011 17:42
Number of views: 45
Video resolution: 1024x576 px, 512x288 px
Video length: 0:14:22
Audio track: MP3 [4.82 MB], 0:14:22