A pairwise discriminant approach using artificial neural networks for continuous speech recognition

スポンサーリンク

概要

• 論文の詳細を見る

• This paper describes a pairwise discrimination approach using artificial neural networks for robust phoneme recognition and its application to continuous speech recognition. Until now, it is known that classification-type neural networks show poor robustness against the robustness, we developed Pairwise Discriminant Time-Delay Neural Networks(PD-TDNNs)by applying the principle of pair discrimination scores for all combinations of two phonemes are calculated by PD-TDNNs, each of which has a less sharp discrimination boundary, and final phoneme candidates are decided by majority decision of the pair discrimination scores. Through phoneme and continuous speech recognition experiments, it was found that this approach performs better than the conventional TDNN.

• 社団法人日本音響学会の論文

著者

• Sagayama S

  Ntt Human Interface Lab. Yokosuka‐shi Jpn

• Sagayama Shigeki

  ATR Interpreting Telephony Research Laboratories

• Takami Jun-ichi

  ATR Interpreting Telephony Research Laboratories

• Kai Atsuhiko

  Department of Information and Computer Sciences,Toyohashi University of Technology

• Kai Atsuhiko

  Department Of Information And Computer Sciences Toyohashi University Of Technology

• Takami J

  Kumamoto National Hospital Kumamoto

• Takami Jun-ichi

  Atr Interpreting Telecommunications 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
• Relationship among Recognition Rate, Rejection Rate and False Alarm Rate in a Spoken Word Recognition System
• Speaker Adaptation Based on Vector Field Smoothing
• Minimum error classification training of HMMs : Implementation details and experimental results
• Unsupervised Speaker Adaptation Using All-Phoneme Ergodic Hidden Markov Network
• 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)

スポンサーリンク