SuperLectures.com

INFORMATIVE DIALECT RECOGNITION USING CONTEXT-DEPENDENT PRONUNCIATION MODELING

Full Paper at IEEE Xplore

Language Identification

Presented by: Nancy Chen, Author(s): Nancy Chen, Massachusetts Institute of Technology, United States; Wade Shen, Joseph Campbell, Pedro Torres-Carrasquillo, MIT Lincoln Laboratory, United States

We propose an informative dialect recognition system that learns phonetic transformation rules, and uses them to identify dialects. A hidden Markov model is used to align reference phones with dialect-specific pronunciations to characterize when and how often substitutions, insertions, and deletions occur. Decision tree clustering is used to find context-dependent phonetic rules. We ran recognition tasks on 4 Arabic dialects. Not only do the proposed systems perform well on their own, but when fused with baselines they improve performance by 21-36% relative. In addition, our proposed decision-tree system beats the baseline monophone system in recovering phonetic rules by 21% relative. Pronunciation rules learned by our proposed system quantify the occurrence frequency of known rules, and suggest rule candidates for further linguistic studies.


  Speech Transcript

|

  Slides

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

0:00:16

  1. slide

0:02:16

  2. slide

0:04:24

  3. slide

0:05:14

  4. slide

0:06:07

  5. slide

0:08:13

  6. slide

0:08:43

  7. slide

0:09:21

  8. slide

0:09:51

  9. slide

0:10:30

 10. slide

0:10:57

 11. slide

0:11:38

 12. slide

0:12:05

 13. slide

0:12:55

 14. slide

0:13:23

 15. slide

0:13:41

 16. slide

0:14:14

 17. slide

0:15:02

 18. slide

  Comments

Please sign in to post your comment!

  Lecture Information

Recorded: 2011-05-24 10:35 - 10:55, Panorama
Added: 23. 6. 2011 17:40
Number of views: 56
Video resolution: 1024x576 px, 512x288 px
Video length: 0:21:00
Audio track: MP3 [7.09 MB], 0:21:00