A Study of Variable-Parameter Gaussian Mixture Hidden Markov Modeling for Noisy Speech Recognition

@article{Cui2007ASO,
  title={A Study of Variable-Parameter Gaussian Mixture Hidden Markov Modeling for Noisy Speech Recognition},
  author={Xiaodong Cui and Yifan Gong},
  journal={IEEE Transactions on Audio, Speech, and Language Processing},
  year={2007},
  volume={15},
  pages={1366-1376}
}
To improve recognition performance in noisy environments, multicondition training is usually applied in which speech signals corrupted by a variety of noise are used in acoustic model training. Published hidden Markov modeling of speech uses multiple Gaussian distributions to cover the spread of the speech distribution caused by noise, which distracts the modeling of speech event itself and possibly sacrifices the performance on clean speech. In this paper, we propose a novel approach which… CONTINUE READING
Highly Cited
This paper has 52 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 27 extracted citations

Convolutional neural network bottleneck features for bi-directional generalized variable parameter HMMs

2016 IEEE International Conference on Information and Automation (ICIA) • 2016
View 1 Excerpt

Automatic Complexity Control of Generalized Variable Parameter HMMs for Noise Robust Speech Recognition

IEEE/ACM Transactions on Audio, Speech, and Language Processing • 2015
View 3 Excerpts

An Overview of Noise-Robust Automatic Speech Recognition

IEEE/ACM Transactions on Audio, Speech, and Language Processing • 2014
View 8 Excerpts

52 Citations

051015'10'13'16'19
Citations per Year
Semantic Scholar estimates that this publication has 52 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 28 references

Evaluation of Mel-Wiener filter for Mel-LPC based speech recognition

M. B. Islam, H. Matsumoto, K. Yamamoto
Proc. Int. Conf. Speech Comput., 2005, pp. 531–534. • 2005
View 1 Excerpt

Noise-dependent Gaussian mixture classifiers for robust rejection decision

IEEE Trans. Speech and Audio Processing • 2002
View 1 Excerpt

Noise-dependent open-set, speaker recognition using noise-dependent Gaussian mixture classifier

——
Proc. IEEE Int. Conf. Acoust., Speech, Signal Process., 2002. • 2002

Similar Papers

Loading similar papers…