Presentation | 2015-11-12 Noise suppression method for body-conducted soft speech based on external noise monitoring Yusuke Tajiri, Tomoki Toda, Satoshi Nakamura, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | As one of the silent speech interfaces, nonaudible murmur (NAM) microphone has been developed for detecting an extremely soft speech through the soft tissue.In recent years, several enhancement methods based on statistical voice conversion techniques have also been proposed to improve the quality of body-conducted speech, and their effectiveness has been confirmed in a quiet environment. However, it is expected that the NAM microphone will be used not only in quiet, but also in noisy environments. Although the NAM microphone is robust against external noise compared to a usual air-conductive microphone, it is difficult to completely block the external noise signals. Therefore, their effect on the body-conducted speech signal cannot be ignored. In particular, when detecting soft speech like NAM or a whispered voice, its body-conducted speech signal easily suffers from the external noise signals because power of soft speech is too small. To address this issue, we propose a noise suppression method for the body-conducted soft speech based on external noise monitoring using an air-conductive microphone. Experimental results demonstrate that the proposed method yields 10 dB SNR improvements in 80 dBA noisy conditions and also yields significant improvements in sound quality of body-conducted soft speech. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | silent speech communication / nonaudible murmur / noise suppression / external noise monitoring / semi-blind source separation |
Paper # | EA2015-31,EMM2015-52 |
Date of Issue | 2015-11-05 (EA, EMM) |
Conference Information | |
Committee | EA / EMM |
---|---|
Conference Date | 2015/11/12(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Kumamoto Univ. |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Multimedia Fusion, Content Processing, Multimedia Retrieval, Digital Watermarking, and Related Topics |
Chair | Yoichi Haneda(Univ. of Electro-Comm.) / Akinori Ito(Tohoku Univ.) |
Vice Chair | Yukio Iwaya(Tohoku Gakuin Univ.) / Mitsunori Mizumachi(Kyushu Inst. of Tech.) / Masashi Unoki(JAIST) / Masaki Kawamura(Yamaguchi Univ.) |
Secretary | Yukio Iwaya(NTT) / Mitsunori Mizumachi(KDDI R&D Labs.) / Masashi Unoki(Univ. of Electro-Comm.) / Masaki Kawamura(Nagasaki Univ.) |
Assistant | Shoichi Koyama(Univ. of Tokyo) / Motoi Iwata(Osaka Pref. Univ.) / Kazuhiro Kohno(Kansai Univ.) |
Paper Information | |
Registration To | Technical Committee on Engineering Acoustics / Technical Committee on Enriched MultiMedia |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Noise suppression method for body-conducted soft speech based on external noise monitoring |
Sub Title (in English) | |
Keyword(1) | silent speech communication |
Keyword(2) | nonaudible murmur |
Keyword(3) | noise suppression |
Keyword(4) | external noise monitoring |
Keyword(5) | semi-blind source separation |
1st Author's Name | Yusuke Tajiri |
1st Author's Affiliation | Nara Institute of Science and Technology(NAIST) |
2nd Author's Name | Tomoki Toda |
2nd Author's Affiliation | Nagoya University(Nagoya Univ.) |
3rd Author's Name | Satoshi Nakamura |
3rd Author's Affiliation | Nara Institute of Science and Technology(NAIST) |
Date | 2015-11-12 |
Paper # | EA2015-31,EMM2015-52 |
Volume (vol) | vol.115 |
Number (no) | EA-302,EMM-303 |
Page | pp.pp.41-46(EA), pp.41-46(EMM), |
#Pages | 6 |
Date of Issue | 2015-11-05 (EA, EMM) |