講演名 2004/12/13
Asynchronous Articulatory Feature Recognition Using Dynamic Bayesian Networks
,
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) This paper builds on previous work where dynamic Bayesian networks (DBN) were proposed as a model for articulatory feature recognition. Using DBNs makes it possible to model the dependencies between features, an addition to previous approaches which was found to improve feature recognition performance. The DBN results were promising, giving close to the accuracy of artificial neural nets (ANNs). However, the system was trained on canonical labels, leading to an overly strong set of constraints on feature co-occurrence. In this study, we describe an embedded training scheme which learns a set of data-driven asynchronous feature changes where supported in the data. Using a subset of the OGI Numbers corpus, we describe articulatory feature recognition experiments using both canonically-trained and asynchronous-feature DBNs. Performance using DBNs is found to exceed that of ANNs trained on an identical task, giving a higher recognition accuracy. Furthermore, inter-feature dependencies result in a more structured model, giving rise to fewer feature combinations in the recognition output. In addition to an empirical evaluation of this modeling approach, we give a qualitative analysis, investigating the asynchrony found through our data-driven method and interpreting it using linguistic knowledge.
キーワード(和)
キーワード(英) Articulatory feature recognition / dynamic Bayesian networks
資料番号 NLC2004-47,SP2004-87
発行日

研究会情報
研究会 NLC
開催期間 2004/12/13(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 Natural Language Understanding and Models of Communication (NLC)
本文の言語 ENG
タイトル(和)
サブタイトル(和)
タイトル(英) Asynchronous Articulatory Feature Recognition Using Dynamic Bayesian Networks
サブタイトル(和)
キーワード(1)(和/英) / Articulatory feature recognition
第 1 著者 氏名(和/英) / Mirjam WESTERN
第 1 著者 所属(和/英)
Centre for Speech Technology Research, University of Edinburgh
発表年月日 2004/12/13
資料番号 NLC2004-47,SP2004-87
巻番号(vol) vol.104
号番号(no) 538
ページ範囲 pp.-
ページ数 6
発行日