JAIST Repository >
b. 情報科学研究科・情報科学系 >
b11. 会議発表論文・発表資料等 >
b11-1. 会議発表論文・発表資料 >

このアイテムの引用には次の識別子を使用してください: http://hdl.handle.net/10119/9580

タイトル: Voice activity detection in a regularized reproducing kernel Hilbert space
著者: Lu, Xugang
Unoki, Masashi
Isotani, Ryosuke
Kawai, Hisashi
Nakamura, Satoshi
キーワード: Statistical learning
reproducing kernel Hilbert space
voice activity detection
発行日: 2010-09
出版者: International Speech Communication Association
誌名: Proceedings of INTERSPEECH 2010
開始ページ: 3086
終了ページ: 3089
抄録: Voice activity detection (VAD) is used to detect whether the acoustic signal belongs to speech or non-speech clusters based on the statistical distribution of the acoustic features. Traditional VAD algorithms are applied in a linear transformed space without any constraint relating to the special characteristics speech or noise. As a result, the VAD algorithms are not robust to noise interference. Considering that speech is a special type of acoustic signal that only occupies a small fraction of the whole acoustic space, we proposed a new speech feature extraction method by giving constraints on the processing space as a reproducing kernel Hilbert space (RKHS). In the RKHS, we regarded the speech estimation as a functional approximation problem, and estimated the approximation function via a regularized framework in the RKHS. Under this framework, we could incorporate the nonlinear mapping functions in the approximation implicitly via a kernel function. The approximation function could capture the nonlinear and high-order statistical regularities of the speech. Our VAD algorithm is designed on the basis of the power energy in this regularized RKHS. Compared with a baseline and G.729B VAD algorithms, experimental results showed the promising advantages of our proposed algorithm.
Rights: Copyright (C) 2010 International Speech Communication Association. Xugang Lu, Masashi Unoki, Ryosuke Isotani, Hisashi Kawai, and Satoshi Nakamura, Proceedings of INTERSPEECH 2010, 2010, 3086-3089.
URI: http://hdl.handle.net/10119/9580
資料タイプ: publisher
出現コレクション:b11-1. 会議発表論文・発表資料 (Conference Papers)

このアイテムのファイル:

ファイル 記述 サイズ形式
15957-1.pdf320KbAdobe PDF見る/開く

当システムに保管されているアイテムはすべて著作権により保護されています。

 


お問い合わせ先 : 北陸先端科学技術大学院大学 研究推進課図書館情報係