SuperLectures.com

A SYMMETRIZATION OF THE SUBSPACE GAUSSIAN MIXTURE MODEL

Acoustic Modeling

Full Paper at IEEE Xplore

Přednášející: Daniel Povey, Autoři: Daniel Povey, Microsoft Corporation, United States; Martin Karafiát, Brno University of Technology, Czech Republic; Arnab Ghoshal, University of Saarland, Czech Republic; Petr Schwarz, Brno University of Technology, Czech Republic

Last year we introduced the Subspace Gaussian Mixture Model (SGMM), and we demonstrated Word Error Rate improvements on a fairly small-scale task. Here we describe an extension to the SGMM, which we call the symmetric SGMM. It makes the model fully symmetric between the ``speech-state vectors'' and ``speaker vectors'' by making the mixture weights depend on the speaker as well as the speech state. We find that the symmetric SGMM can give a very worthwhile improvement over the previously described model. We will also describe some larger-scale experiments with the SGMM, and report on progress toward releasing open-source software that supports SGMMs.


  Přepis řeči

|

  Slajdy

Zvětšit slajd | Zobrazit všechny slajdy

0:00:16

  1. slajd

0:00:41

  2. slajd

0:01:41

  3. slajd

0:02:07

  4. slajd

0:02:36

  5. slajd

0:03:58

  6. slajd

0:05:37

  7. slajd

0:06:55

  8. slajd

0:09:09

  9. slajd

0:09:21

     8. slajd

0:10:05

 10. slajd

0:11:01

 11. slajd

0:12:18

 12. slajd

0:12:41

 13. slajd

0:13:42

 14. slajd

0:14:07

 15. slajd

0:14:33

 16. slajd

0:14:48

 17. slajd

0:15:01

 18. slajd

0:15:37

 19. slajd

  Komentáře

Please sign in to post your comment!

  Informace o přednášce

Nahráno: 2011-05-25 15:05 - 15:25, Panorama
Přidáno: 15. 6. 2011 16:17
Počet zhlédnutí: 182
Rozlišení videa: 1024x576 px, 512x288 px
Délka videa: 0:19:39
Audio stopa: MP3 [6.64 MB], 0:19:39