An investigation of deep neural networks for noise robust speech recognition

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn , Issue , 2013, Pages 7398-7402

  Seltzer, Michael L ^a   Yu, Dong ^a   Wang, Yongqiang ^b  

^a MICROSOFT RESEARCH   (United States)

^b UNIVERSITY OF CAMBRIDGE   (United Kingdom)

Author keywords

adaptive training; Aurora 4; deep neural network; noise robustness

Indexed keywords

ADAPTIVE TRAINING; AURORA 4; DECODING COMPLEXITY; DEEP NEURAL NETWORKS; NOISE ROBUST SPEECH RECOGNITION; NOISE ROBUSTNESS; STATE-OF-THE-ART PERFORMANCE; TRAINING TECHNIQUES;

DECODING; NEURAL NETWORKS; SIGNAL PROCESSING;

ACOUSTIC NOISE;

EID: 84890492030     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2013.6639100     Document Type: Conference Paper

References (26)

1. D. Macho, L. Mauuary, B. Noe, Y.M. Cheng, D. Ealey, D. Jou-vet, H. Kelleher, D. Pearce, and F. Saadoun, "Evaluation of a noise-robust DSR front-end on Aurora databases," in Proc. of ICSLP, Denver, Colorado, 2002.
2. D. Yu, L. Deng, J. Droppo, J. Wu, Y. Gong, and A. Acero, "A Minimum-mean-square-error noise reduction algorithm on mel-frequency cepstra for robust speech recognition," in Proc. of ICASSP, Las Vegas, NV, 2008.
3. J. Li, L. Deng, D. Yu, Y. Gong, and A. Acero, "High-performance HMM adaptation with joint compensation of ad-ditive and convolutive distortions via Vector Taylor Series," in Proc. of ASRU, Kyoto, Japan, 2007.
4. Y. Hu and Q. Huo, "An HMM compensation approach us-ing unscented transformation for noisy speech recognition," in Proc. ISCSLP, 2006, pp. 346-357.
5. M. L. Seltzer, K. Kalgaonkar, and A. Acero, "Acoustic model adaptation via linear spline interpolation for robust speech recognition," in Proc. of ICASSP, Dallas, TX, 2010.
6. M. L. Seltzer, Techniques for Noise Robustness in Automatic Speech Recognition, chapter Acoustic Model Training for Ro-bust Speech Recognition, John Wiley, 2013.
7. O. Kalinli, M. L. Seltzer, J. Droppo, and A. Acero, "Noise adaptive training for robust automatic speech recognition," Au-dio, Speech, and Language Processing, IEEE Transactions on, vol. 18, no. 8, pp. 1889-1901, Nov. 2010.
8. H. Liao and M. J. F. Gales, "Adaptive training with joint uncer-tainty decoding for robust recognition of noisy data," in Proc. of ICASSP, Honolulu, Hawaii, 2007.
9. S. Renals, N. Morgan, H. Bourlard, M. Cohen, and H. Franco, "Connectionist probability estimators in HMM speech recog-nition," IEEE Trans. Speech and Audio Proc., jan 1994.
10. A. Mohamed, G.E. Dahl, and G. Hinton, "Acoustic modeling using deep belief networks," Audio, Speech, and Language Processing, IEEE Transactions on, vol. 20, no. 1, pp. 14-22, jan. 2012.
11. F. Seide, G. Li, and D. Yu, "Conversational speech transcrip-tion using context-dependent deep neural networks," in Proc. Interspeech, 2011.
12. B. Kingsbury, T. N. Sainath, and H. Soltau, "Scalable mini-mum bayes risk training of deep neural network acoustic mod-els using distributed hessian-free optimization," in Proc. Inter-speech, 2012.
13. O. Vinyals and S.V. Ravuri, "Comparing multilayer perceptron to deep belief network tandem features for robust asr," in Proc. ICASSP, may 2011, pp. 4596-4599.
14. S. Sharma, D. Ellis, S. Kajarekar, P. Jain, and H. Hermansky, "Feature extraction using non-linear transformation for robust speech recognition on the aurora database," in Proc. ICASSP, 2000, vol. 2, pp. II1117-II1120 vol.2.
15. S. Tamura and A.Waibel, "Noise reduction using connectionist models," in Proc. ICASSP, apr 1988, pp. 553-556 vol.1.
16. Andrew L. Maas, Quoc V. Le, Tyler M. ONeil, Oriol Vinyals, Patrick Nguyen, and Andrew Y. Ng, "Recurrent neural net-works for noise reduction in robust ASR," in Proc. Interspeech, 2012.
17. G. E. Hinton, N. Srivastava, A. Krizhevsky, I. Sutskever, and R. R. Salakhutdinov, "Improving neural net-works by preventing co-adaptation of feature detectors," http://arxiv.org/abs/1207.0580, 2012.
18. Lawrence Saul, Tommi Jaakkola, and Michael I. Jordan, "Mean field theory for sigmoid belief networks," Journal of Artificial Intelligence Research, vol. 4, pp. 61-76, 1996.
19. G. Hinton, "A practical guide to training restricted boltzmann machines," Tech. Rep. UTML TR
20. Li Deng, A. Acero, Mike Plumpe, and Huang Xuedong, "Large-vocabulary speech recognition under adverse acoustic environments," ICSLP 2000, vol. 3, pp. 806-809, October 2000.
21. Y. Ephraim and D. Malah, "Speech enhancement using a minimum mean square error log-spectral amplitude estimator," IEEE Trans. on Acoust., Speech, Signal Processing, vol. ASSP-33, no. 2, pp. 443-445, Apr. 1985.
22. A. Acero, L. Deng, T. Kristjansson, and J. Zhang, "HMM Adaptation Using Vector Taylor Series for Noisy Speech Recognition," in Proc. of ICSLP, 2000.
23. N. Parihar and J. Picone, "Aurora working group: DSR front end LVCSR evaluation AU/384/02," Tech. Rep., Inst. for Sig-nal and Information Process, Mississippi State University.
24. F. Flego and M. J. F. Gales, "Discriminative adaptive training with VTS and JUD," in IEEE Workshop on Automatic Speech Recognition and Understanding, 2009, pp. 170-175.
25. A. Ragni and M. J. F. Gales, "Derivative kernels for noise robust ASR," in IEEE Workshop on Automatic Speech Recog-nition and Understanding, 2011.
26. Y.-Q. Wang and M. J. F. Gales, "Speaker and noise factori-sation for robust speech recognition," IEEE transactions on audio speech and language processing, vol. 20, no. 7, 2012.