| 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］Accent Analysis for Mandarin Large Vocabulary Continuous Speech Recognition ○Dong Yang・Koji Iwano・Sadaoki Furui（Tokyo Inst. of Tech.）  SP2007-201 |
|
| 抄録 | （和） | This paper presents our work on accent issues in Mandarin large vocabulary continuous speech recognition. What we want to address in this paper are two questions about Mandarin: whether accents affect speech recognition greatly; how we can solve the problem. For the first question, we know that, across a vast region and a huge population, there are varieties of accented Mandarin spoken in China, which are mainly caused by speakers' dialects. In accented Mandarin, the dominant problem is mispronunciations of three types of confusions. We summarize them in this paper and focus on their effects on speech recognition for each speaker. For the second question, we try to perform maximum likelihood linear regression (MLLR) adaptation for each speaker and then analyze the recognition results. We find that up to 45% of the accent related errors get corrected for accented speakers and there is no such improvement for standard speakers. Our experimental analysis and result support us to conclude that the accent is a serious problem in Mandarin speech recognition and the MLLR adaptation is effective in reducing the mismatch caused by accents. |
| （英） | This paper presents our work on accent issues in Mandarin large vocabulary continuous speech recognition. What we want to address in this paper are two questions about Mandarin: whether accents affect speech recognition greatly; how we can solve the problem. For the first question, we know that, across a vast region and a huge population, there are varieties of accented Mandarin spoken in China, which are mainly caused by speakers' dialects. In accented Mandarin, the dominant problem is mispronunciations of three types of confusions. We summarize them in this paper and focus on their effects on speech recognition for each speaker. For the second question, we try to perform maximum likelihood linear regression (MLLR) adaptation for each speaker and then analyze the recognition results. We find that up to 45% of the accent related errors get corrected for accented speakers and there is no such improvement for standard speakers. Our experimental analysis and result support us to conclude that the accent is a serious problem in Mandarin speech recognition and the MLLR adaptation is effective in reducing the mismatch caused by accents. | |
| キーワード | （和） | Analysis of Mandarin accents / large vocabulary continuous speech recognition / accent adaptation / / / / / |
| （英） | Analysis of Mandarin accents / large vocabulary continuous speech recognition / accent adaptation / / / / / | |
| 文献情報 | 信学技報, vol. 107, no. 551, SP2007-201, pp. 87-92, 2008年3月. | |
| 資料番号 | SP2007-201 | |
| 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 | SP2007-201 |
|
| 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） | Accent Analysis for Mandarin Large Vocabulary Continuous Speech Recognition |
| サブタイトル（英） | |
| キーワード(1)（和/英） | Analysis of Mandarin accents / Analysis of Mandarin accents |
| キーワード(2)（和/英） | large vocabulary continuous speech recognition / large vocabulary continuous speech recognition |
| キーワード(3)（和/英） | accent adaptation / accent adaptation |
| キーワード(4)（和/英） | / |
| キーワード(5)（和/英） | / |
| 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） | Dong Yang / Dong Yang / |
| 第1著者 所属（和/英） | Tokyo Institute of Technology (略称： 東工大) Tokyo Institute of Technology (略称： Tokyo Inst. of Tech.) |
| 第2著者 氏名（和/英/ヨミ） | Koji Iwano / Koji Iwano / |
| 第2著者 所属（和/英） | Tokyo Institute of Technology (略称： 東工大) Tokyo Institute of Technology (略称： Tokyo Inst. of Tech.) |
| 第3著者 氏名（和/英/ヨミ） | Sadaoki Furui / Sadaoki Furui / |
| 第3著者 所属（和/英） | Tokyo Institute of Technology (略称： 東工大) Tokyo Institute of Technology (略称： Tokyo Inst. of Tech.) |
| 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 | SP2007-201 |
| 巻番号（vol） | vol.107 |
| 号番号（no） | no.551 |
| ページ範囲 | pp.87-92 |
| 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]