Dynamic integration of multiple feature streams for robust real-time LVCSR

Shoei Sato*, Kazuo Onoe, Kio Kobayashi, Shinich Homma, Torn Imai, Tohru Takagi, Tetsunori Kobayashi

*この研究の対応する著者

研究成果: Conference contribution

抄録

We present a novel method of integrating the likelihoods of multiple feature streams for robust speech recognition. The integration algorithm dynamically calculates a frame-wise stream weight so that a heavier weight is given to a stream that is robust to a variety of noisy environments or speaking styles. Such a robust stream is expected to bring out discriminative ability. The weight is calculated in real time from mutual information between an input stream and active HMM states in a search space. In this paper, we describe three features that are extracted through auditory filters by taking into account the human auditory system extracting amplitude and frequency modulations. These features are expected to provide complementary clues for speech recognition. Speech recognition experiments using field reports and spontaneous commentary from Japanese broadcast news showed that the proposed method reduced error words by 9% relative to the best result obtained from a single stream.

本文言語English
ホスト出版物のタイトルInternational Speech Communication Association - 8th Annual Conference of the International Speech Communication Association, Interspeech 2007
ページ345-348
ページ数4
出版ステータスPublished - 2007 12月 1
イベント8th Annual Conference of the International Speech Communication Association, Interspeech 2007 - Antwerp, Belgium
継続期間: 2007 8月 272007 8月 31

出版物シリーズ

名前Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
1
ISSN(電子版)1990-9772

Conference

Conference8th Annual Conference of the International Speech Communication Association, Interspeech 2007
国/地域Belgium
CityAntwerp
Period07/8/2707/8/31

ASJC Scopus subject areas

  • コンピュータ サイエンスの応用
  • ソフトウェア
  • モデリングとシミュレーション
  • 言語学および言語
  • 通信

フィンガープリント

「Dynamic integration of multiple feature streams for robust real-time LVCSR」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