| 電子情報通信学会 研究会発表申込システム 講演論文 詳細 |
技報閲覧サービス [ログイン] 技報アーカイブ |
| トップに戻る | 前のページに戻る | [Japanese] / [English] |
| 講演抄録／キーワード | ||
| 講演名 | 2008-03-20 15:15 ［ポスター講演］Robust Distant Speech Recognition by Combining Variable-term spectrum Based Position-dependent CMN with Conventional CMN ○Longbiao Wang・Seiichi Nakagawa（Toyohashi Univ. of Tech.）・Norihide Kitaoka（Nagoya Univ.）  SP2007-197 |
|
| 抄録 | （和） | In a distant-talking environment, the duration 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. |
| （英） | In a distant-talking environment, the duration 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） | Robust speech recognition / distant-talking environments / dereverberation / position-dependent CMN / conventional CMN / / / |
| （英） | Robust speech recognition / distant-talking environments / dereverberation / position-dependent CMN / conventional CMN / / / | |
| 文献情報 | 信学技報, vol. 107, no. 551, SP2007-197, pp. 63-68, 2008年3月. | |
| 資料番号 | SP2007-197 | |
| 発行日 | 2008-03-13 (SP) | |
| ISSN | Print edition: ISSN 0913-5685 Online edition: ISSN 2432-6380 | |
| 著作権に ついて |
技術研究報告に掲載された論文の著作権は電子情報通信学会に帰属します．(許諾番号：10GA0019/12GB0052/13GB0056/17GB0034/18GB0034) | |
| PDFダウンロード | SP2007-197 |
|
| 研究会情報 | |
| 研究会 | SP |
| 開催期間 | 2008-03-20 - 2008-03-21 |
| 開催地（和） | 東大 |
| 開催地（英） | Univ. Tokyo |
| テーマ（和） | 国際ワークショップ(20日），研究会(21日) 「聴覚・音声・言語とその障害，一般」 |
| テーマ（英） | International Workshop (Mar 20), Speech Production, Speech Perception, Hearing and Speech, etc. (Mar 21) |
| 講演論文情報の詳細 | |
| 申込み研究会 | SP |
| 会議コード | 2008-03-SP |
| 本文の言語 | 英語 |
| タイトル（和） | |
| サブタイトル（和） | |
| タイトル（英） | Robust Distant Speech Recognition by Combining Variable-term spectrum Based Position-dependent CMN with Conventional CMN |
| サブタイトル（英） | |
| キーワード(1)（和/英） | Robust speech recognition / Robust speech recognition |
| キーワード(2)（和/英） | distant-talking environments / distant-talking environments |
| キーワード(3)（和/英） | dereverberation / dereverberation |
| キーワード(4)（和/英） | position-dependent CMN / position-dependent CMN |
| キーワード(5)（和/英） | conventional CMN / conventional CMN |
| キーワード(6)（和/英） | / |
| キーワード(7)（和/英） | / |
| キーワード(8)（和/英） | / |
| 第1著者 氏名（和/英/ヨミ） | Longbiao Wang / Longbiao Wang / |
| 第1著者 所属（和/英） | Toyohashi University of Technology (略称： 豊橋技科大) Toyohashi University of Technology (略称： Toyohashi Univ. of Tech.) |
| 第2著者 氏名（和/英/ヨミ） | Seiichi Nakagawa / Seiichi Nakagawa / |
| 第2著者 所属（和/英） | Toyohashi University of Technology (略称： 豊橋技科大) Toyohashi University of Technology (略称： Toyohashi Univ. of Tech.) |
| 第3著者 氏名（和/英/ヨミ） | Norihide Kitaoka / Norihide Kitaoka / |
| 第3著者 所属（和/英） | Nagoya University (略称： 名大) Nagoya University (略称： Nagoya Univ.) |
| 講演者 | 第1著者 |
| 発表日時 | 2008-03-20 15:15:00 |
| 発表時間 | 90分 |
| 申込先研究会 | SP |
| 資料番号 | SP2007-197 |
| 巻番号（vol） | vol.107 |
| 号番号（no） | no.551 |
| ページ範囲 | pp.63-68 |
| ページ数 | 6 |
| 発行日 | 2008-03-13 (SP) |
[研究会発表申込システムのトップページに戻る]