Presentation 1996/11/15
Speech Segmentation under Noisy and Musical Circumstancies by Subspace Method
Motohiro Kashihara, Yasuo Ariki,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this study, extraction of speech section was experimented under circumstancies with white Gaussian noise. The extraction rate by a subspace method was 100 percent to the noisy speech with 0dB S/N ratios by 128 point FFT analysis. Furthermore, the extraction of speech section was experimented by LPC cepstrum analysis in a similar way and compared with the FFT analysis, and confirmed that LPC cepstrum analysis is more effective than FFT spectrum analysis under white gaussian noise circumstancies. Next, we tried to extract the speech section under musical circumstancies in a similar way.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) subspace method / CLAFIC method / projection length / LPC cepstrum / FFT spectrum / white Gaussian noise
Paper # SP96-62
Date of Issue

Conference Information
Committee SP
Conference Date 1996/11/15(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 Speech (SP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Speech Segmentation under Noisy and Musical Circumstancies by Subspace Method
Sub Title (in English)
Keyword(1) subspace method
Keyword(2) CLAFIC method
Keyword(3) projection length
Keyword(4) LPC cepstrum
Keyword(5) FFT spectrum
Keyword(6) white Gaussian noise
1st Author's Name Motohiro Kashihara
1st Author's Affiliation Faculty of Science and Technology, Ryukoku University()
2nd Author's Name Yasuo Ariki
2nd Author's Affiliation Faculty of Science and Technology, Ryukoku University
Date 1996/11/15
Paper # SP96-62
Volume (vol) vol.96
Number (no) 364
Page pp.pp.-
#Pages 6
Date of Issue