SuperLectures.com

ANALYSIS-SYNTHESIS BASED SPEECH ENHANCEMENT WITH IMPROVED SPECTRUM ENVELOPE ESTIMATION BY TRACKING SPEECH DYNAMICS

Full Paper at IEEE Xplore

Speech Enhancement

Presented by: Ruofei chen, Author(s): Ruofei Chen, Cheung-Fat Chan, City University of Hong Kong, Hong Kong SAR of China

This paper presents a Kalman tracking approach to re-estimate clean spectral amplitude from noisy speech spectrum for re-synthesis based speech enhancement. The motivation of using Kalman filter and training is to exploit the temporal correlation between speech dynamics and to include prior knowledge of speech to improve the model parameter estimation in harmonic noise model (HNM) based speech enhancement system. The re-estimated harmonic amplitude is fitted into an analysis-synthesis framework to accomplish a more accurate HNM based re-synthesis. Objective evaluation results show the proposed method achieves significant improvement over various classical short-time spectral amplitude (STSA) based methods, especially in low signal-to-noise ratio environments.

  Speech Transcript

|

  Slides

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

0:00:16

  1. slide

0:00:36

  2. slide

0:01:16

  3. slide

0:01:45

  4. slide

0:03:14

  5. slide

0:03:51

  6. slide

0:04:37

  7. slide

0:05:43

  8. slide

0:06:20

  9. slide

0:07:24

 10. slide

0:07:58

 11. slide

0:08:32

 12. slide

0:08:57

 13. slide

0:09:36

 14. slide

0:10:43

 15. slide

0:11:07

 16. slide

0:11:37

 17. slide

0:12:47

 18. slide

0:13:13

 19. slide

0:13:49

 20. slide

0:14:29

 21. slide

  Comments

Please sign in to post your comment!

  Lecture Information

Recorded: 2011-05-27 17:15 - 17:35, Panorama
Added: 9. 6. 2011 04:56
Number of views: 46
Video resolution: 1024x576 px, 512x288 px
Video length: 0:18:18
Audio track: MP3 [6.25 MB], 0:18:18