SuperLectures.com

AN SVM BASED CLASSIFICATION APPROACH TO SPEECH SEPARATION

Full Paper at IEEE Xplore

Speech Enhancement

Presented by: Kun Han, Author(s): Kun Han, DeLiang Wang, The Ohio State University, United States

Monaural speech separation is a very challenging task. CASA-based systems utilize acoustic features to produce a time-frequency (T-F) mask. In this study, we propose a classification approach to monaural separation problem. Our feature set consists of pitch-based features and amplitude modulation spectrum features, which can discriminate both voiced and unvoiced speech from nonspeech interference. We employ support vector machines (SVMs) followed by a re-thresholding method to classify each T-F unit as either target-dominated or interference-dominated. An auditory segmentation stage is then utilized to improve SVM-generated results. Systematic evaluations show that our approach produces high quality binary masks and outperforms a previous system in terms of classification accuracy.

  Speech Transcript

|

  Slides

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

0:00:16

  1. slide

0:00:36

  2. slide

0:00:59

  3. slide

0:01:37

  4. slide

0:02:52

  5. slide

0:03:52

  6. slide

0:04:43

  7. slide

0:05:45

  8. slide

0:06:13

  9. slide

0:07:14

 10. slide

0:08:18

 11. slide

0:09:43

 12. slide

0:10:07

 13. slide

0:11:21

 14. slide

0:12:26

 15. slide

0:13:39

 16. slide

0:14:55

 17. slide

0:15:40

 18. slide

  Comments

Please sign in to post your comment!

  Lecture Information

Recorded: 2011-05-27 16:15 - 16:35, Panorama
Added: 7. 6. 2011 19:19
Number of views: 48
Video resolution: 1024x576 px, 512x288 px
Video length: 0:20:25
Audio track: MP3 [6.98 MB], 0:20:25