SuperLectures.com

A TOOLKIT FOR SPEECH RECOGNITION RESEARCH

Presented by: Dan Povey, Author(s): Dan Povey

This talk introduces the Kaldi speech recognition toolkit: a new speech recognition toolkit written in C++ that uses FSTs for training and testing. It uses the OpenFst library and links against BLAS and LAPACK for linear algebra support. The aim is to create a clean, flexible and well-structured toolkit for speech recognition researchers.

  Speech Transcript

|

  Slides

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

0:00:16

  1. slide

0:02:09

  2. slide

0:03:58

  3. slide

0:05:56

  4. slide

0:09:12

  5. slide

0:12:29

  6. slide

0:13:55

  7. slide

0:14:44

  8. slide

0:15:31

  9. slide

0:19:49

 10. slide

0:21:55

 11. slide

0:23:30

 12. slide

0:25:42

 13. slide

0:27:10

 14. slide

0:29:21

 15. slide

0:30:35

 16. slide

0:32:21

 17. slide

0:34:10

 18. slide

0:37:24

 19. slide

0:39:50

 20. slide

0:41:27

 21. slide

0:45:16

 22. slide

0:45:22

 23. slide

0:46:33

 24. slide

0:47:44

 25. slide

0:49:26

 26. slide

0:50:39

 27. slide

0:52:23

 28. slide

  Comments

Please sign in to post your comment!

  Lecture Information

Recorded: 2011-05-27 13:00 - 14:00, Room 3.3
Added: 23. 6. 2011 01:36
Number of views: 246
Video resolution: 1024x576 px, 512x288 px
Video length: 0:54:23
Audio track: MP3 [18.57 MB], 0:54:23