Browse > Article

Phonetic Question Set Generation Algorithm  

김성아 (고려대학교 컴퓨터학과 음성정보처리 연구실)
육동석 (고려대학교 컴퓨터학과 음성정보처리 연구실)
권오일 (현대 오토넷 주식회사)
Abstract
Due to the insufficiency of training data in large vocabulary continuous speech recognition, similar context dependent phones can be clustered by decision trees to share the data. When the decision trees are built and used to predict unseen triphones, a phonetic question set is required. The phonetic question set, which contains categories of the phones with similar co-articulation effects, is usually generated by phonetic or linguistic experts. This knowledge-based approach for generating phonetic question set, however, may reduce the homogeneity of the clusters. Moreover, the experts must adjust the question sets whenever the language or the PLU (phone-like unit) of a recognition system is changed. Therefore, we propose a data-driven method to automatically generate phonetic question set. Since the proposed method generates the phone categories using speech data distribution, it is not dependent on the language or the PLU, and may enhance the homogeneity of the clusters. In large vocabulary speech recognition experiments, the proposed algorithm has been found to reduce the error rate by 14.3%.
Keywords
Phonetic question set; Decision tree; State clustering; Large vocabulary continuous speech recognition; Context dependent acoustic model;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Tree-based state tying for high accuracy acoustic modeling /
[ S.Young;J.Odell;P.Woodland ] / DARPA Human Language Technology Workshop
2 The use of context in large vocabulary speech recognition /
[ J.Odell ] / PhD thesis, University of Cambridge
3 Decision tree based clustering /
[ D.Yook ] / Lecture Notes in Computer Science
4 Unsupervised incremental online adaptation to unknown environment and speaker /
[ D.Yook ] / Proc. of the IEEE International Conference on Acoustics, Speech, and Signal Processing
5 Context-dependent phonetic hidden Markov models for speaker-independent continuous speech recognition /
[ K.Lee ] / IEEE Transactions on Acoustics, Speech, and Signal Processing   ScienceOn
6 Hidden Markov model and neural network hybrid /
[ D.Yook ] / Lecture Notes in Computer Science
7 /
[ K.Fukunaga ] / Introduction to Statistical Pattern Recognition
8 Automatic clustering and generation of contextual questions for tied states in hidden Markov models /
[ R.Singh;B.Raj;R.Stern ] / Proc. of the IEEE International Conference on Acoustics, Speech, and Signal Processing
9 Automatic question generation for decision tree based state tying /
[ K.Beulen;H.Ney ] / Proc. of the IEEE International Conference on Acoustics, Speech, and Signal Processing
10 Predicting unseen triphones with senones /
[ M.Hwang;X.Huang;F.Alleva ] / IEEE Transactions on Speech and Audio Processing   ScienceOn