Speaker Adaptation Based on Vector Field Smoothing

スポンサーリンク

概要

• 論文の詳細を見る

• This paper describes a new supervised speaker adaptation method based on vector field smoothing, for small size adaptation data. This method assumes that the correspondence of feature vectors between speakers can be viewed as a kind of smooth vector field, and interpolation and smoothing of the correspondence are introduced into the adaptation process for higher adaptation performance with small size data. The proposed adaptation method was applied to discrete HMM based speech recognition and evaluated in Japanese phoneme and phrase recognition experiments. Using 10 words as the adaptation data, the proposed method produced almost the same results as the conventional codebook mapping method with 25 words. These experiments clearly confirmed the effectiveness of the proposed method.

• 社団法人電子情報通信学会の論文
• 1993-02-25

著者

• Sagayama Shigeki

  ATR Interpreting Telephony Research Laboratories

• Hattori Hiroaki

  ATR Interpreting Telephony Research Laboratories

関連論文

• A voice conversion based on phoneme segment mapping
• LR Parsing with a Category Reachability Test Applied to Speech Recognition (Special Issue on Speech and Discourse Processing in Dialogue Systems)
• A pairwise discriminant approach using artificial neural networks for continuous speech recognition
• Speaker Weighted Training of HMM Using Multiple Reference Speakers
• Speaker Adaptation Based on Vector Field Smoothing
• Minimum error classification training of HMMs : Implementation details and experimental results
• Isolated Word Recognition Using Pitch Pattern Information
• Three Different LR Parsing Algorithms for Phoneme-Context-Dependent HMM-Based Continuous Speech Recognition (Special Issue on Speech and Discourse Processing in Dialogue Systems)
• Text-Independent Speaker Recognition Using Neural Networks

スポンサーリンク