A SYMMETRIZATION OF THE SUBSPACE GAUSSIAN MIXTURE MODEL
Acoustic Modeling
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.
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 |
Příbuzné přednášky
0:20:42
CLUSTERING OF BOOTSTRAPPED ACOUSTIC MODEL WITH FULL COVARIANCE
Acoustic Modeling
Přidáno: 15. 6. 2011 16:00
0:20:20
AN INVESTIGATION OF SUBSPACE MODELING FOR PHONETIC AND SPEAKER VARIABILITY IN AUTOMATIC SPEECH RECOGNITION
Acoustic Modeling
Přidáno: 15. 6. 2011 17:03
Komentáře