MINIMUM BAYES RISK ESTIMATION AND DECODING IN LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION

スポンサーリンク

概要

• 論文の詳細を見る

• Minimum risk estimation and decoding strategies based on lattice segmentation techniques can be used to refine large vocabulary continuous speech recognition systems through the estimation of the parameters of the underlying hidden Mark models and through the identification of smaller recognition tasks which provides the opportunity to incorporate novel modeling and decoding procedures in LVCSR. These techniques are discussed in the context of going 'beyond HMMs'.

• 社団法人電子情報通信学会の論文
• 2004-12-13

著者

• Byrne William

  Department Of Engineering Cambridge University

関連論文

• Invited: Minimum Bayes Risk Estimation and Decoding in Large Vocabulary Continuous Speech Recognition (国際ワークショップ"Beyond HMM")
• MINIMUM BAYES RISK ESTIMATION AND DECODING IN LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION

スポンサーリンク