| 講演名 | 2008-03-20 Robust Distant Speech Recognition by Combining Variable-trem spectrum Based Position-dependent CMN with Conventional CMN , |
|---|---|
| PDFダウンロードページ |  PDFダウンロードページへ |
| 抄録(和) | |
| 抄録(英) | In a distant-talking environment, the length of channel impulse response is longer than the short-term spectral analysis window. Therefore, the conventional short-term spectrum based Cepstral Mean Normalization (CMN) is not effective under these conditions. In this paper, we propose a robust distant speech recognition method by combining a short-term spectrum based CMN with a long-term one. We assume that a static speech segment (such as a vowel, for example) affected by reverberation can be modeled by a long-term cepstral analysis. Thus, the effect of long reverberation on a static speech segment may be compensated by the long-term spectrum based CMN. In this paper, the concept of combining short-term and long-term spectrum based CMN is extended to an environmentally robust speech recognition method based on Position-Dependent CMN (PDCMN). We call this Variable Term spectrum based PDCMN (VT-PDCMN). Since PDCMN/VT-PDCMN cannot normalize speaker variations, we also combine PDCMN/VT-PDCMN with conventional CMN in this study. We conducted the experiments based on our proposed method using limited vocabulary (100 words) distant-talking isolated word recognition in a real environment. The proposed method achieved a relative error reduction rate of 60.9% over the conventional short-term spectrum based CMN and 30.6% over the short-term spectrum based PDCMN. |
| キーワード(和) | |
| キーワード(英) | Robust speech recognition / distant-talking environments / dereverberation / position-dependent CMN / conventional CMN |
| 資料番号 | SP2007-197 |
| 発行日 |
| 研究会情報 | |
| 研究会 | SP |
|---|---|
| 開催期間 | 2008/3/13(から1日開催) |
| 開催地（和） | |
| 開催地（英） | |
| テーマ（和） | |
| テーマ（英） | |
| 委員長氏名（和） | |
| 委員長氏名（英） | |
| 副委員長氏名（和） | |
| 副委員長氏名（英） | |
| 幹事氏名（和） | |
| 幹事氏名（英） | |
| 幹事補佐氏名（和） | |
| 幹事補佐氏名（英） | |
| 講演論文情報詳細 | |
| 申込み研究会 | Speech (SP) |
|---|---|
| 本文の言語 | ENG |
| タイトル（和） | |
| サブタイトル（和） | |
| タイトル（英） | Robust Distant Speech Recognition by Combining Variable-trem spectrum Based Position-dependent CMN with Conventional CMN |
| サブタイトル（和） | |
| キーワード(1)（和/英） | / Robust speech recognition |
| 第 1 著者 氏名（和/英） | / Longbiao WANG |
| 第 1 著者 所属（和/英） | Department of Information and Computer Sciences, Toyohashi University of Technology |
| 発表年月日 | 2008-03-20 |
| 資料番号 | SP2007-197 |
| 巻番号（vol） | vol.107 |
| 号番号（no） | 551 |
| ページ範囲 | pp.- |
| ページ数 | 6 |
| 発行日 | |