论文信息 - Language identification using Gaussian mixture model tokenization

Language identification using Gaussian mixture model tokenization

Phone tokenization followed by n-gram language modeling has consistently provided good results for the task of language identification. In this paper, this technique is generalized by using Gaussian mixture models as the basis for tokenizing. Performance results are presented for a system employing a GMM tokenizer in conjunction with multiple language processing and score combination techniques. On the 1996 CallFriend LID evaluation set, a 12-way closed set error rate of 17% was obtained.

[1] Marc A. Zissman,et al. Automatic language identification using Gaussian mixture and hidden Markov models , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[2] Frederick Jelinek,et al. Statistical methods for speech recognition , 1997 .

[3] Douglas A. Reynolds,et al. A study of computation speed-UPS of the GMM-UBM speaker recognition system , 1999, EUROSPEECH.

[4] Marc A. Zissman,et al. Comparison of : Four Approaches to Automatic Language Identification of Telephone Speech , 2004 .

[5] Frédéric Bimbot,et al. Inference of variable-length acoustic units for continuous speech recognition , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[6] Shigeo Abe DrEng. Pattern Classification , 2001, Springer London.