Presentation 2003/9/22
Speech/Music Discrimination using HMM
Toru TANIGUCHI, Akishige ADACHI, Shigeki OKAWA, Katsuhiko SHIRAI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Speech/Music discrimination has been studied for various applications such as automatic indexing of audio data. In this report, we suggest a method using HMM to discriminate speech and music. Although the HMM is simple left-to-right HMM, experimental results showed this method achieves higher discrimination rate than conventional feature-based method. And with Seven HMM categorized more detailed than category of speech and music, more speech and music sounds were correctly discriminated than with speech and music HMM.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Speech/Music discrimination / HMM / Audio retrieval
Paper # DSP2003-97,SP2003-92
Date of Issue

Conference Information
Committee DSP
Conference Date 2003/9/22(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Digital Signal Processing (DSP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Speech/Music Discrimination using HMM
Sub Title (in English)
Keyword(1) Speech/Music discrimination
Keyword(2) HMM
Keyword(3) Audio retrieval
1st Author's Name Toru TANIGUCHI
1st Author's Affiliation School of Science and Engineering, Waseda University()
2nd Author's Name Akishige ADACHI
2nd Author's Affiliation School of Science and Engineering, Waseda University
3rd Author's Name Shigeki OKAWA
3rd Author's Affiliation Dept. Network Science, Chiba Institute of Technology
4th Author's Name Katsuhiko SHIRAI
4th Author's Affiliation School of Science and Engineering, Waseda University
Date 2003/9/22
Paper # DSP2003-97,SP2003-92
Volume (vol) vol.103
Number (no) 329
Page pp.pp.-
#Pages 5
Date of Issue