Authors: Shunsuke Ishimitsu, Masashi Nakayama, Seiji Nakagawa
Addresses: Graduate School of Information Sciences, Hiroshima City University, 3-3-1 Ozuka-Higashi, Asa-Minami-Ku, Hiroshima, Japan. ' Graduate School of Information Sciences, Hiroshima City University, 3-3-1 Ozuka-Higashi, Asa-Minami-Ku, Hiroshima, Japan. ' Institute for Human Science and Biomedical Engineering, National Institute of Advanced Industrial Science and Technology (AIST), 1-8-31 Midorigaoka, Ikeda, Osaka, Japan
Abstract: Speech recognition tends to be influenced by noise in the air. Body-conducted speech offers a robust signal extraction method from noisy environments, particularly because body-conducted speech is a propagated sound and not easily influenced by noise. However, when body-conducted speech is extracted with an accelerator, the typical frequency component of 2 kHz or more decreases compared with normal speech. Thus, we investigated a technique combining differential acceleration and noise reduction to estimate a clear signal using only body-conducted speech from a noisy room. The recognition rate confirmed about 3-4% is improved with proposed method.
Keywords: body-conducted speech; differential acceleration; speech retrieval; Wiener filtering; speech recognition; robust signal extraction; noisy environments; noise reduction.
International Journal of Advanced Mechatronic Systems, 2010 Vol.2 No.4, pp.246 - 253
Available online: 07 Jun 2010 *Full-text access for editors Access for subscribers Purchase this article Comment on this article