Search error risk minimization in viterbi beam search for speech recognition

Takaaki Hori, Shinji Watanabe, Atsushi Nakamura

研究成果: Conference contribution

2 被引用数 (Scopus)

抄録

This paper proposes a method to optimize Viterbi beam search based on search error risk minimization in large vocabulary continuous speech recognition (LVCSR). Most speech recognizers employ beam search to speed up the decoding process, in which unpromising partial hypotheses are pruned during decoding. However, the pruning step involves the risk of missing the best complete hypothesis by discarding a partial hypothesis that might grow into the best. Missing the best hypothesis is called search error. Our purpose is to reduce search error by optimizing the pruning step. While conventional methods use heuristic criteria to prune each hypothesis based on its score, rank, and so on, our proposed method introduces a pruning function that makes a more precise decision using the rich features extracted from each hypothesis. The parameters of the function can be estimated efficiently to minimize the search error risk using recognition lattices at the training step. We implemented the new method in a WFST-based decoder and achieved a significant reduction of search errors in a 200K-word LVCSR task.

本文言語English
ホスト出版物のタイトル2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010 - Proceedings
ページ4934-4937
ページ数4
DOI
出版ステータスPublished - 2010 11 8
外部発表はい
イベント2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010 - Dallas, TX, United States
継続期間: 2010 3 142010 3 19

出版物シリーズ

名前ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISSN(印刷版)1520-6149

Conference

Conference2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010
国/地域United States
CityDallas, TX
Period10/3/1410/3/19

ASJC Scopus subject areas

  • ソフトウェア
  • 信号処理
  • 電子工学および電気工学

フィンガープリント

「Search error risk minimization in viterbi beam search for 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