Decoding network optimization using minimum transition error training

Yotaro Kubo, Shinji Watanabe, Atsushi Nakamura

研究成果: Conference contribution

5 被引用数 (Scopus)

抄録

The discriminative optimization of decoding networks is important for minimizing speech recognition error. Recently, several methods have been reported that optimize decoding networks by extending weighted finite state transducer (WFST)-based decoding processes to a linear classification process. In this paper, we model decoding processes by using conditional random fields (CRFs). Since the maximum mutual information (MMI) training technique is straightforwardly applicable for CRF training, several sophisticated training methods proposed as the variants of MMI can be incorporated in our decoding network optimization. This paper adapts the boosted MMI and the differenced MMI methods for decoding network optimization so that state transition errors are minimized in WFST decoding. We evaluated the proposed methods by conducting large-vocabulary continuous speech recognition experiments. We confirmed that the CRF-based framework and transition error minimization are efficient for improving the accuracy of automatic speech recognizers.

本文言語English
ホスト出版物のタイトル2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012 - Proceedings
ページ4197-4200
ページ数4
DOI
出版ステータスPublished - 2012 10 23
外部発表はい
イベント2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012 - Kyoto, Japan
継続期間: 2012 3 252012 3 30

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

Conference2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012
国/地域Japan
CityKyoto
Period12/3/2512/3/30

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

「Decoding network optimization using minimum transition error training」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