Adaptation of precision matrix models on large vocabulary continuous speech recognition
暂无分享,去创建一个
[1] Mark J. F. Gales,et al. Investigation of acoustic modeling techniques for LVCSR systems , 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..
[2] Mark J. F. Gales,et al. Maximum likelihood linear transformations for HMM-based speech recognition , 1998, Comput. Speech Lang..
[3] Mark J. F. Gales,et al. Semi-tied covariance matrices for hidden Markov models , 1999, IEEE Trans. Speech Audio Process..
[4] Mark J. F. Gales,et al. Maximum likelihood multiple projection schemes for hidden Markov models , 1999 .
[5] Mark J. F. Gales,et al. Mean and variance adaptation within the MLLR framework , 1996, Comput. Speech Lang..
[6] Jing Huang,et al. Large vocabulary conversational speech recognition with the extended maximum likelihood linear transformation (EMLLT) model , 2002, INTERSPEECH.
[7] Scott Axelrod,et al. Modeling with a subspace constraint on inverse covariance matrices , 2002, INTERSPEECH.
[8] Brian Kingsbury,et al. Large vocabulary conversational speech recognition with a subspace constraint on inverse covariance matrices , 2003, INTERSPEECH.
[9] Peder A. Olsen,et al. Modeling inverse covariance matrices by basis expansion , 2002, IEEE Transactions on Speech and Audio Processing.
[10] Khe Chai Sim,et al. Precision matrix modelling for large vocabulary continuous speech recognition , 2004 .