Unsupervised Online Adaptation of Segmental Switching Linear Gaussian Hidden Markov Models for Robust Speech Recognition
暂无分享,去创建一个
[1] Jian Wu,et al. Discriminative speaker adaptation and environmental robustness in automatic speech recognition , 2004 .
[2] Qiang Huo,et al. An environment compensated maximum likelihood training approach based on stochastic vector mapping [speech recognition applications] , 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..
[3] Chin-Hui Lee,et al. A maximum-likelihood approach to stochastic matching for robust speech recognition , 1996, IEEE Trans. Speech Audio Process..
[4] Yifan Gong,et al. A general joint additive and convolutive bias compensation approach applied to noisy Lombard speech recognition , 1998, IEEE Trans. Speech Audio Process..
[5] Qiang Huo,et al. A study of minimum classification error training for segmental switching linear Gaussian hidden Markov models , 2004, INTERSPEECH.
[6] David Pearce,et al. The aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions , 2000, INTERSPEECH.
[7] Qiang Huo,et al. A switching linear Gaussian hidden Markov model and its application to nonstationary noise compensation for robust speech recognition , 2003, INTERSPEECH.
[8] Qiang Huo,et al. A study of switching state segmentation in segmental switching linear Gaussian hidden Markov models for robust speech recognition , 2004, 2004 International Symposium on Chinese Spoken Language Processing.