SuperLectures.com

AN UTTERANCE COMPARISON MODEL FOR SPEAKER CLUSTERING USING FACTOR ANALYSIS

Full Paper at IEEE Xplore

Miscellaneous Speaker Identification

Přednášející: Woojay Jeon, Autoři: 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.


  Přepis řeči

|

  Slajdy

Zvětšit slajd | Zobrazit všechny slajdy

0:00:16

  1. slajd

0:00:24

  2. slajd

0:01:18

  3. slajd

0:02:14

  4. slajd

0:02:46

  5. slajd

0:03:22

  6. slajd

0:03:28

     5. slajd

0:03:34

     6. slajd

0:04:23

  7. slajd

0:06:24

  8. slajd

0:07:11

  9. slajd

0:08:29

 10. slajd

0:08:50

 11. slajd

0:09:16

 12. slajd

0:10:14

 13. slajd

0:10:25

 14. slajd

0:10:46

 15. slajd

0:11:21

 16. slajd

0:12:23

 17. slajd

0:13:33

 18. slajd

0:13:49

 19. slajd

  Komentáře

Please sign in to post your comment!

  Informace o přednášce

Nahráno: 2011-05-25 17:35 - 17:55, Panorama
Přidáno: 15. 6. 2011 16:56
Počet zhlédnutí: 59
Rozlišení videa: 1024x576 px, 512x288 px
Délka videa: 0:17:31
Audio stopa: MP3 [5.91 MB], 0:17:31