Multi-stream acoustic model adaptation for noisy speech recognition

Satoshi Tamura*, Satoru Hayamizu

*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, a multi-stream-based model adaptation method is proposed for speech recognition in noisy or real environments. The proposed scheme comes from our experience about audio-visual model adaptation. At first, an acoustic feature vector is divided into several vectors (e.g. static, first-order and second-order dynamic vectors), namely streams. While adaptation, a stream performing relatively high recognition performance is updated for the stream only. Alternatively, a stream having less recognition power is adapted using all the streams that are superior to the stream. In order to evaluate the proposed technique, recognition experiments were conducted using every streams, and then adaptation experiments were also investigated for various types of combination of streams.

本文言語English
ホスト出版物のタイトル2012 Conference Handbook - Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2012
出版ステータスPublished - 2012
外部発表はい
イベント2012 4th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2012 - Hollywood, CA, United States
継続期間: 2012 12 32012 12 6

出版物シリーズ

名前2012 Conference Handbook - Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2012

Other

Other2012 4th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2012
国/地域United States
CityHollywood, CA
Period12/12/312/12/6

ASJC Scopus subject areas

  • 情報システム

フィンガープリント

「Multi-stream acoustic model adaptation for noisy speech recognition」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