Presentation 1999/12/20
Environmental Sound Discrimination Based on Hidden Markov Model
Kazuhiro MIKI, Takanobu NISHIURA, Satoshi NAKAMURA, Kiyohiro SHIKANO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In real acoustic environments, human communicates each other through speech by focusing on the target speech sound among environmental sounds. We can easily discriminate the target sound from other environmental sounds. For hands-free speech recognition, the discrimination of the target speech from environmental sounds is inevitable. This mechanism might also be important even for the self moving robot to sense acoustic environments and communicate with human. This paper proposes HMM-based environmental sound recognition. Environmental sounds are modeled by three state HMMs and evaluated using 90 kinds of environmental sounds. The recognition accuracy was 95.4%. Thi spaper also proposes recognition of the environment sound-added is olatedwords by HMM composition. The experiments show the HMM composition of speech HMMs and a HMM of classe environmental sounds outperforms the conventional HMM composition of speech HMMs and a noise HMMt trained using noise periods prior to the target speech in the environments.
Keyword(in Japanese) (See Japanese page)
Keyword(in English)
Paper # NLC99-106
Date of Issue

Conference Information
Committee NLC
Conference Date 1999/12/20(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 Natural Language Understanding and Models of Communication (NLC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Environmental Sound Discrimination Based on Hidden Markov Model
Sub Title (in English)
Keyword(1)
1st Author's Name Kazuhiro MIKI
1st Author's Affiliation ()
2nd Author's Name Takanobu NISHIURA
2nd Author's Affiliation
3rd Author's Name Satoshi NAKAMURA
3rd Author's Affiliation
4th Author's Name Kiyohiro SHIKANO
4th Author's Affiliation
Date 1999/12/20
Paper # NLC99-106
Volume (vol) vol.99
Number (no) 523
Page pp.pp.-
#Pages 6
Date of Issue