SuperLectures.com

AN UTTERANCE COMPARISON MODEL FOR SPEAKER CLUSTERING USING FACTOR ANALYSIS

Miscellaneous Speaker Identification

Full Paper at IEEE Xplore

Presented by: Woojay Jeon, Author(s): Woojay Jeon, Changxue Ma, Dusan Macho, Motorola, United States

We propose a novel utterance comparison model based on probability theory and factor analysis that computes the likelihood of two speech utterances originating from the same speaker. The model depends only on a set of statistics extracted from each utterance and can efficiently compare utterances using these statistics without requiring the indefinite storage of speech features. We apply the model as a distance metric for speaker clustering in the CALLHOME telephone conversation corpus to achieve competitive results compared to three other known similarity measures: the Generalized Likelihood Ratio, Cross-Likelihood Ratio, and eigenvoice distance.

  Speech Transcript

|

  Slides

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

0:00:16

  1. slide

0:00:24

  2. slide

0:01:18

  3. slide

0:02:14

  4. slide

0:02:46

  5. slide

0:03:22

  6. slide

0:03:28

     5. slide

0:03:34

     6. slide

0:04:23

  7. slide

0:06:24

  8. slide

0:07:11

  9. slide

0:08:29

 10. slide

0:08:50

 11. slide

0:09:16

 12. slide

0:10:14

 13. slide

0:10:25

 14. slide

0:10:46

 15. slide

0:11:21

 16. slide

0:12:23

 17. slide

0:13:33

 18. slide

0:13:49

 19. slide

  Comments

Please sign in to post your comment!

  Lecture Information

Recorded: 2011-05-25 17:35 - 17:55, Panorama
Added: 15. 6. 2011 16:56
Number of views: 59
Video resolution: 1024x576 px, 512x288 px
Video length: 0:17:31
Audio track: MP3 [5.91 MB], 0:17:31