Quasi-continuous local codebook features for multilingual acoustic phonetic modelling
暂无分享,去创建一个
[1] Albino Nogueiras,et al. The demiphone: an efficient subword unit for continuous speech recognition , 1997, EUROSPEECH.
[2] Albino Nogueiras Rodríguez,et al. The demiphone:an efficient subword unit for Continuous Speech Recognition , 1997 .
[3] Andrej Zgank,et al. Data driven generation of broad classes for decision tree construction in acoustic modeling , 2003, INTERSPEECH.
[4] Hermann Ney,et al. Automatic question generation for decision tree based state tying , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).
[5] Teuvo Kohonen,et al. Self-Organizing Maps , 2010 .
[6] Asunción Moreno,et al. Local Codebook Features for Mono-and Multilingual Acoustic Phonetic Modelling , 2004 .
[7] William J. Byrne,et al. Towards language independent acoustic modeling , 2000, 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100).
[8] Albino Nogueiras,et al. The demiphone: An efficient contextual subword unit for continuous speech recognition , 2000, Speech Commun..
[9] Asunción Moreno,et al. Acoustic phonetic modeling using local codebook features , 2004, INTERSPEECH.
[10] Ciprian Chelba,et al. Mutual information phone clustering for decision tree induction , 2002, INTERSPEECH.