SuperLectures.com

COMBINING HMM-BASED MELODY EXTRACTION AND NMF-BASED SOFT MASKING FOR SEPARATING VOICE AND ACCOMPANIMENT FROM MONAURAL AUDIO

Acoustic Source Separation

Full Paper at IEEE Xplore

Presented by: Yun Wang, Author(s): Yun Wang, Zhijian Ou, Tsinghua University, China

Modern monaural voice and accompaniment separation systems usually consist of two main modules: melody extraction and time-frequency masking. A main distinction between different separation systems lies in what approaches are used for the two modules. Popular techniques for melody extraction include hidden Markov models (HMMs) and non-negative matrix factorization (NMF), and masking includes hard and soft masking. This paper investigates the flaw of NMF-based melody extraction, and proposes the combination of HMM-based melody extraction (equipped with a newly-defined feature) and NMF-based soft masking. Evaluations on two publicly available databases show that the proposed system reaches state-of-the-art performance and outperforms several other combinations.


  Speech Transcript

|

  Slides

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

0:01:08

  1. slide

0:01:23

  2. slide

0:02:31

  3. slide

0:03:17

  4. slide

0:03:44

  5. slide

0:05:28

  6. slide

0:06:36

  7. slide

0:09:33

  8. slide

0:10:58

  9. slide

0:11:48

 10. slide

0:13:01

 11. slide

0:13:35

 12. slide

0:15:32

 13. slide

0:16:27

 14. slide

0:18:16

 15. slide

0:19:35

    14. slide

  Comments

Please sign in to post your comment!

  Lecture Information

Recorded: 2011-05-24 10:15 - 10:35, Club H
Added: 7. 6. 2011 19:19
Number of views: 133
Video resolution: 1024x576 px, 512x288 px
Video length: 0:20:41
Audio track: MP3 [7.07 MB], 0:20:41