SuperLectures.com

MPTRACKER: A NEW MULTI-PITCH DETECTION AND SEPARATION ALGORITHM FOR MIXED SPEECH SIGNALS

Speech Analysis

Full Paper at IEEE Xplore

Presented by: Hossein Radfar, Author(s): Hossein Radfar, University of Toronto, Canada; R. M. Dansereau, Carleton University, Canada; Wai-Yip Chan, Queen's University Belfast, Canada; W. Wong, University of Toronto, Canada

We present MPtracker, a new algorithm for tracking and separating the pitch frequencies of two speakers from their mixture. The pitch frequencies are detected by introducing a novel spectral distortion optimization which takes into account the sinusoidal modeling of the speech signal. The detected pitch frequencies are grouped, separated, and finally an interpolation method is applied to estimate missing pitch frequencies. We evaluated the performance of the proposed technique on 196 mixtures including 48 male-male, 48 female-female, and 96 male-female mixtures with target-to-interference ratios (TIR) ranging from 0 dB to +18 dB. The results show our simple but effective and fast technique significantly outperforms two widely-used approaches


  Speech Transcript

|

  Slides

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

0:00:21

  1. slide

0:00:51

  2. slide

0:02:38

  3. slide

0:03:26

  4. slide

0:04:40

  5. slide

0:05:11

  6. slide

0:06:31

  7. slide

0:07:32

  8. slide

0:08:17

  9. slide

0:09:04

 10. slide

0:10:04

 11. slide

0:10:50

 12. slide

0:11:26

 13. slide

0:12:06

 14. slide

0:13:23

 15. slide

0:14:46

 16. slide

0:15:10

 17. slide

  Comments

Please sign in to post your comment!

  Lecture Information

Recorded: 2011-05-25 09:50 - 10:10, Panorama
Added: 15. 6. 2011 15:18
Number of views: 33
Video resolution: 1024x576 px, 512x288 px
Video length: 0:19:22
Audio track: MP3 [6.54 MB], 0:19:22