Browse > Article

Performance Improvement in Speech Recognition by Weighting HMM Likelihood  

권태희 (고려대학교 전자.컴퓨터공학과)
고한석 (고려대학교 전자.컴퓨터공학과)
Abstract
In this paper, assuming that the score of speech utterance is the product of HMM log likelihood and HMM weight, we propose a new method that HMM weights are adapted iteratively like the general MCE training. The proposed method adjusts HMM weights for better performance using delta coefficient defined in terms of misclassification measure. Therefore, the parameter estimation and the Viterbi algorithms of conventional 1:.um can be easily applied to the proposed model by constraining the sum of HMM weights to the number of HMMs in an HMM set. Comparing with the general segmental MCE training approach, computing time decreases by reducing the number of parameters to estimate and avoiding gradient calculation through the optimal state sequence. To evaluate the performance of HMM-based speech recognizer by weighting HMM likelihood, we perform Korean isolated digit recognition experiments. The experimental results show better performance than the MCE algorithm with state weighting.
Keywords
Hidden Markov modeling; Minimum classification error; HMM likelihood weight; Delta coefficient;
Citations & Related Records
연도 인용수 순위
  • Reference
1 /
[ L.Rabiner;B.H.Juang ] / Fundamentals of Speech Recognition
2 An improved approach to robust speech recognition using minimum error classification /
[ M.T.Lin;A.Spanias;P.Loizou ] / Speech Communication   ScienceOn
3 An improved maximum model distance approach for HMM-based speech recognition systems /
[ A.H.He;S.Kwong;K.F.Man;K.S.Tang ] / Pattern Recognition   ScienceOn
4 Performance of HMM-based speech recognizers with discriminative state-weights /
[ O.W.Kwon;C.K.Un ] / Speech Communication   ScienceOn
5 Discriminative learning for minimum error classification /
[ B.H.Juang;S.Katagiri ] / IEEE Transactions on Signal Processing   ScienceOn
6 Minimum error rate training based on N-best string models /
[ W.Chou;C.H.Lee;B.H.Juang ] / IEEE ICASSP-93
7 Discriminant-function-based minimum recognition error rate pattern-recognition approach to speech recognition /
[ W.Chou ] / Proceedings of the IEEE   ScienceOn
8 Improved generalization of MCE parameter estimation with application to speech recognition /
[ D.W.Purnell;E.C.Botha ] / IEEE Transactions on Speech and Audio Processing   ScienceOn
9 Estimating hidden markov model parameters so as to maximize speech recognition accuracy /
[ L.R.Bahl;P.F.Brown;P.V. de Souza;R.L.Mercer ] / IEEE Transactions on Speech and Audio Processing   ScienceOn
10 Minimum classification error rate methods for speech recognition /
[ B.H.Juang;W.Chou;C.H.Lee ] / IEEE Transactions on Speech and Audio Processing   ScienceOn
11 /
[ X.Huang;A.Acero;H.W.Hon ] / Spoken Language Processing