Maximum likelihood modelling of pronunciation variation

Speech Communication - Tập 29 - Trang 177-191 - 1999
Trym Holter1, Torbjørn Svendsen2
1Department of Signal Processing and Systems Design, SINTEF Telecom and Informatics, O.S. Bragstads plass 2, 7465 Trondheim, Norway
2Department of Telecommunications, Norwegian University of Science and Technology, Norway

Tài liệu tham khảo

Bacchiani, M., Ostendorf, M., 1998. Joint acoustic design and lexicon generation. In: Proceedings of the ESCA Workshop on Modeling Pronunciation Variation for Automatic Speech Recognition. ESCA, Rolduc, The Netherlands. pp. 7–12

Bahl, 1993, A method for the construction od acoustic markov models for words, IEEE Trans. Speech Audio Process., 1, 442, 10.1109/89.242490

Holter, T., 1997. Maximum likelihood modelling of pronunciation in automatic speech recognition. Ph.D. Thesis, Norwegian University of Science and Technology

Klatt, 1987, Review of text-to-speech conversion for English, J. Acoust. Soc. Amer., 82, 737, 10.1121/1.395275

Lu, 1978, A sentence-to-sentence clustering procedure for pattern analysis, IEEE Trans. Syst. Man Cybernet. SMC, 8, 381, 10.1109/TSMC.1978.4309979

Nilsson, 1971

NIST Speech Disc 2-4.2, 1992. Resource Management continuous speech database (RM1) – Development test and evaluation test data and scoring software

Young, S.J., Jansen, J., Odell, J., Ollason, D., Woodland, P., 1993. HTK: Hidden Markov Model Toolkit V1.5. Cambridge University Engineering Department Speech Group and Entropic Research Laboratories

Zhao, 1993, A speaker-independent continuous speech recognition system using continuous mixture Gaussian density HMM of phoneme-sized units, IEEE Trans. Speech Audio Process., 1, 345, 10.1109/89.232618