| 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 11:00 ［招待講演］Robust Speech Recognition Based on Structured Modeling, Irrelevant Variability Normalization and Unsupervised Online Adaptation ○Qiang Huo（Microsoft Research Asia）  SP2007-186 |
|
| 抄録 | （和） | In the past several years, we've been studying several approaches to robust automatic speech recognition (ASR) based on three key concepts, namely structured modeling, irrelevant variability normalization (IVN) and unsupervised online adaptation (OLA). In structured modeling of basic speech units, speech information relevant to phonetic classification is modeled by traditional hidden Markov models (HMMs), while factors irrelevant to phonetic classification are taken care of by an auxiliary module. An IVN-based training procedure can then be designed to estimate parameters of the generic HMMs and the auxiliary module from a large amount of diversified training data. In recognition stage, the parameters of the auxiliary module can be updated via unsupervised OLA by using the unknown utterance itself, which is recognized again to achieve a better performance by using the compensated models composed from the generic HMMs and the adapted auxiliary module. In this talk, I will explain the above key concepts and methodology, and elaborate on several robust ASR techniques thereof, which have achieved the state-of-the-art performance over the years on both Aurora2 and Aurora3 tasks. |
| （英） | In the past several years, we've been studying several approaches to robust automatic speech recognition (ASR) based on three key concepts, namely structured modeling, irrelevant variability normalization (IVN) and unsupervised online adaptation (OLA). In structured modeling of basic speech units, speech information relevant to phonetic classification is modeled by traditional hidden Markov models (HMMs), while factors irrelevant to phonetic classification are taken care of by an auxiliary module. An IVN-based training procedure can then be designed to estimate parameters of the generic HMMs and the auxiliary module from a large amount of diversified training data. In recognition stage, the parameters of the auxiliary module can be updated via unsupervised OLA by using the unknown utterance itself, which is recognized again to achieve a better performance by using the compensated models composed from the generic HMMs and the adapted auxiliary module. In this talk, I will explain the above key concepts and methodology, and elaborate on several robust ASR techniques thereof, which have achieved the state-of-the-art performance over the years on both Aurora2 and Aurora3 tasks. | |
| キーワード | （和） | / / / / / / / |
| （英） | / / / / / / / | |
| 文献情報 | 信学技報, vol. 107, no. 551, SP2007-186, pp. 3-4, 2008年3月. | |
| 資料番号 | SP2007-186 | |
| 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 | SP2007-186 |
|
| 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 Speech Recognition Based on Structured Modeling, Irrelevant Variability Normalization and Unsupervised Online Adaptation |
| サブタイトル（英） | |
| キーワード(1)（和/英） | / |
| キーワード(2)（和/英） | / |
| キーワード(3)（和/英） | / |
| 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） | Qiang Huo / Qiang Huo / |
| 第1著者 所属（和/英） | Microsoft Research Asia (略称： Microsoft Research Asia) Microsoft Research Asia (略称： Microsoft Research Asia) |
| 講演者 | 第1著者 |
| 発表日時 | 2008-03-20 11:00:00 |
| 発表時間 | 60分 |
| 申込先研究会 | SP |
| 資料番号 | SP2007-186 |
| 巻番号（vol） | vol.107 |
| 号番号（no） | no.551 |
| ページ範囲 | pp.3-4 |
| ページ数 | 2 |
| 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]