|
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/10119/10821
|
| タイトル: | Speech enhancement technique in noisy reverberant environment using two microphone arrays |
| 著者: | Sasaki, Yuuki
Akagi, Masato |
| 発行日: | 2012-03-05 |
| 出版者: | 2012 International Workshop on Nonlinear Circuits, Communications and Signal Processing (NCSP'12) |
| 誌名: | 2012 International Workshop on Nonlinear Circuits, Communications and Signal Processing (NCSP'12) |
| 開始ページ: | 333 |
| 終了ページ: | 336 |
| 抄録: | Recent years, speech enhancement techniques in order to suppress noise and/or reverberation have been introduced into applications like hearing-aid. However, proposed speech enhancement techniques supporting selective binaural selective hearing cannot work in noisy reverberant environment. This paper aims at constructing speech enhancement supporting binaural selective hearing in noisy reverberant environment. Experiment I verifies whether Two–Stage Binaural Speech Enhancement with Wiener Filter (TS–BASE/WF) can suppress early reflection and late reverberation. Results show that TS–BASE/WF cannot suppress early refractions due to using a wiener filter. Cepstral mean subtraction (CMS) is used as front–end of TS–BASE/WF based on this result. Experiment II is carried out to show whether the modified method is superior to TS–BASE/WF in noisy reverberant environments. This result indicates that the modified method exceeds TS–BASE/WF. |
| Rights: | This material is posted here with permission of the Research Institute of Signal Processing Japan. Yuuki Sasaki and Masato Akagi, 2012 International Workshop on Nonlinear Circuits, Communications and Signal Processing (NCSP'12), 2012, pp.333-336. |
| URI: | http://hdl.handle.net/10119/10821 |
| 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 |
|---|
| 1157.pdf | | 286Kb | Adobe 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。
|
