SuperLectures.com

COMPARING MULTILAYER PERCEPTRON TO DEEP BELIEF NETWORK TANDEM FEATURES FOR ROBUST ASR

Full Paper at IEEE Xplore

Robust ASR

Přednášející: Oriol Vinyals, Autoři: Oriol Vinyals, Suman Ravuri, University of California Berkeley, United States

In this paper, we extend the work done on integrating multilayer perceptron (MLP) networks with HMM systems via the Tandem approach. In particular, we explore whether the use of Deep Belief Networks (DBN) adds any substantial gain over MLPs on the Aurora2 speech recognition task under mismatched noise conditions. Our findings suggest that DBNs outperform single layer MLPs under the clean condition, but the gains diminish as the noise level is increased. Furthermore, using MFCCs in conjunction with the posteriors from DBNs outperforms merely using single DBNs in low to moderate noise conditions. MFCCs, however, do not help for the high noise settings.


  Přepis řeči

|

  Slajdy

Zvětšit slajd | Zobrazit všechny slajdy

0:00:16

  1. slajd

0:00:40

  2. slajd

0:02:16

  3. slajd

0:04:42

  4. slajd

0:06:27

  5. slajd

0:07:26

  6. slajd

0:08:13

  7. slajd

0:13:47

  8. slajd

0:14:34

  9. slajd

0:16:20

     4. slajd

  Komentáře

Please sign in to post your comment!

  Informace o přednášce

Nahráno: 2011-05-26 17:15 - 17:35, Panorama
Přidáno: 15. 6. 2011 19:11
Počet zhlédnutí: 39
Rozlišení videa: 1024x576 px, 512x288 px
Délka videa: 0:21:00
Audio stopa: MP3 [7.10 MB], 0:21:00