Classification of causes of speech recognition errors using attention-based bidirectional long short-term memory and modulation spectrum

Jennifer Santoso*, Takeshi Yamada, Shoji Makino

*この研究の対応する著者

研究成果: Conference contribution

1 被引用数 (Scopus)

抄録

In this paper, we address the problem of classifying four common utterance characteristics related to the utterance speed, which cause speech recognition errors. We previously proposed bidirectional long short-term memory (BLSTM) as a classifier and the modulation spectrum as an acoustic feature. However, the performance of it is still insufficient, since BLSTM classified the utterance characteristics from the overall utterance, while most of the recognition errors resulted from utterance characteristics occur in only a small part of utterance. In this paper, we propose an approach to enhance classifier by using attention mechanism (attention-based BLSTM). Attention-based BLSTM enables the classifier to weight each frame according to its importance instead of directly measuring overall information from the speech. Furthermore, we investigate the correspondence of utterance characteristics to different modulation spectrum block lengths. To evaluate the performance of the proposed method, we conducted a classification experiment on Japanese conversational speeches with four different utterance characteristics: 'fast', 'slow', 'filler', and 'stutter'. As a result, the proposed method improved the F-score by 0.033-0.129 compared with the previously proposed method using BLSTM. This result confirms the effectiveness of attention-based BLSTM in classifying cause of errors based on utterance characteristics.

本文言語English
ホスト出版物のタイトル2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2019
出版社Institute of Electrical and Electronics Engineers Inc.
ページ302-306
ページ数5
ISBN(電子版)9781728132488
DOI
出版ステータスPublished - 2019 11
外部発表はい
イベント2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2019 - Lanzhou, China
継続期間: 2019 11 182019 11 21

出版物シリーズ

名前2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2019

Conference

Conference2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2019
国/地域China
CityLanzhou
Period19/11/1819/11/21

ASJC Scopus subject areas

  • 情報システム

フィンガープリント

「Classification of causes of speech recognition errors using attention-based bidirectional long short-term memory and modulation spectrum」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル