Discriminative Training Based on Minimum Classification Error for a Small Amount of Data Enhanced by Vector-Field-Smoothed Bayesian Learning

スポンサーリンク

概要

• 論文の詳細を見る

• This paper describes how to effectively use discriminative training based on Minimum Classification Error (MCE) criterion for a small amount of data in order to attain the highest level of recognition performance. This method is a combination of MCE training and Vector-Field-Smoothed Bayesian learning called MAP/VFS, which combines maximum a posteriori(MAP) estimation with Vector Field Smoothing (VFS). In the proposed method, MAP/VFS can significantly enhance MCE training in the robustness of acoustic modeling. In model training, MCE training is performed using the MAP/VFS-trained model as an initial model. The same data are used in both trainings. For speaker adaptation using several dozen training words,the proposed method has been experimentally proven to be very effective. For 50 word training data, recognition errors are drastically reduced by 47% compared with 16.5% when using only MCE. This high rate, in which 39% is due to MAP, an additional 4% is due to VFS, and a further improvement of 4% is due to MCE, can be attained by enhancing MCE training capability by MAP/VFS.

• 一般社団法人電子情報通信学会の論文
• 1996-12-25

著者

• Sagayama Shigeki

  Ntt Human Interface Laboratories

• TAKAHASHI Jun-ichi

  NTT System Electronics Laboratories

関連論文

• Spoken Sentence Recognition Based on HMM-LR with Hybrid Language Modeling (Special Issue on Natural Language Processing and Understanding)
• LR Parsing with a Category Reachability Test Applied to Speech Recognition (Special Issue on Speech and Discourse Processing in Dialogue Systems)
• Speaker-Consistent Parsing for Speaker-Independent Continuous Speech Recognition
• Automatic Determination of the Number of Mixture Components for Continuous HMMs Based on a Uniform Variance Criterion
• Unsupervised Speaker Adaptation Using All-Phoneme Ergodic Hidden Markov Network
• Speech Recognition Using Function-Word N-Grams and Content-Word N-Grams
• Synthesis of Amino Acids from N_2, H_2O Vapor and CO_2 Gas Mixture by Synchrotron Radiation Induced Photochemical Reactions at Atmospheric Pressure
• Discriminative Training Based on Minimum Classification Error for a Small Amount of Data Enhanced by Vector-Field-Smoothed Bayesian Learning

スポンサーリンク