Feature Compensation

Techniques for Noise Robustness in Automatic Speech Recognition

Volumn , Issue , 2012, Pages 229-250

  Droppo, Jasha ^a  

^a MICROSOFT RESEARCH   (United States)

Author keywords

Acoustic and signals using microphone, linear nonlinear effects; AURORA digital speech recognition, and system evaluation tasks; Discriminative SPLICE and MMI, Aurora 4 and Rprop iterations; Discriminative SPLICE in shortcomings, noise into features; Feature compensation, ideal from observed noisy speech features; Feature enhancement, information and distortion removal; Joint distribution of clean noisy speech model, GMM; MBFE utterance by utterance, SLDM and speech or noise cepstra; MMSE SPLICE in noisy speech, word error rate on Aurora 2; VTS feature enhancement, for processing power and distortion

Indexed keywords

EID: 84886120743     PISSN: None     EISSN: None     Source Type: Book    
DOI: 10.1002/9781118392683.ch9     Document Type: Chapter

References (24)

1. A. Acero and R. M. Stern, "Robust speech recognition by normalization of the acoustic space," in Proceedings of the IEEE ICASSP, vol. 2, pp. 893-896, 1991.
2. L. R. Bahl, P. F. Brown, P. V. D. Souza, and R. L. Mercer, "Maximum mutual information estimation of hidden Markov model parameters for speech recognition," in International Conference on Acoustics, Speech and Signal Processing, 1997.
3. I. Cohen and B. Berdugo, "Noise estimation by minima controlled recursive averaging for robust speech enhancement," IEEE Signal Processing Letters, vol. 9, no. 1, pp. 12-15, 2002.
4. L. Deng, J. Droppo, and A. Acero, "Log-domain speech feature enhancement using sequential map noise estimate and a nonlinear model of acoustic environment," in Proceedings of the ICSLP, Denver, CO, September 2002.
5. L. Deng, J. Droppo, and A. Acero, "Estimating cepstrum of speech under the presence of noise using a joint prior of static and dynamic features," IEEE Transactions on Speech and Audio Processing, vol. 12, no. 3, pp. 218-233, May 2004.
6. V. V. Digalakis, D. Rtischev, and L. G. Neumeyer, "Speaker adaptation using constrained estimation of gaussian mixtures," IEEE Transactions on Speech and Audio Processing, vol. 3, pp. 357-366, September 1995.
7. J. Droppo and A. Acero, "Joint discriminative front end and back end training for improved speech recognition accuracy," in International Conference on Acoustics, Speech and Signal Processing, Toulouse, France, May 2006.
8. J. Droppo and A. Acero, "Noise robust speech recognition with a switching linear dynamic model," in International Conference on Acoustics, Speech and Signal Processing, Montreal, Canada, May 2004.
9. J. Droppo, A. Acero, and L. Deng, "Uncertainty decoding with SPLICE for noise robust speech recognition," in Proceedings of the 2002 ICASSP, Orlando, Florida, May 2002.
10. J. Droppo, L. Deng, and A. Acero, "Evaluation of SPLICE on the Aurora 2 and 3 tasks," in Proceedings of the ICSLP, pp. 29-32, 2002.
11. J. Droppo, L. Deng, and A. Acero, "A comparison of three non-linear observation models for noisy speech features," in Proceedings of the 2003 Eurospeech, Geneva, Switzerland, September 2003, pp. 681-684.
12. J. Droppo, M. Mahajan, A. Gunawardana, and A. Acero, "How to train a discriminative front end with stochastic gradient descent and maximum mutual information," in Proceedings of the IEEE ASRU, 2005.
13. D. Ellis and M. Gomez, "Investigations into tandem acoustic modeling for the Aurora task," in Proceedings of the Eurospeech, 2001, pp. 189-192.
14. B. Frey, L. Deng, A. Acero, and T. Kristjansson, "ALGONQUIN: Iterating Laplace'smethod to remove multiple types of acoustic distortion for robust speech recognition," in Proceedings of the 2001 Eurospeech, Aalbork, Denmark, September 2001.
15. B.-H. Juang,W. Hou, and C.-H. Lee, "Minimum classification error rate methods for speech recognition," IEEE Transactions on Speech and Audio Processing, vol. 5, pp. 257-265, 1997.
16. E. McDermott and S. Katagiri, "Prototype-based minimum classification error/generalized probabilistic descent training for various speech units," Computer Speech & Language, vol. 8, pp. 351-368, 1994.
17. P. Moreno, "Speech recognition in noisy environments," PhD dissertation, Carnegie Mellon University, 1996.
18. P. J. Moreno, B. Raj, E. Gouvea, and R. M. Stern, "Multivariate-gaussian-based cepstral normalization for robust speech recognition," in International Conference on Acoustics, Speech and Signal Processing, 1995, pp. 137-140.
19. Y. Normandin, "Hidden Markov models, maximum mutual information estimation and the speech recognition problem," PhD dissertation, McGill University, 1991.
20. D. Povey, "Discriminative training for large vocabulary speech recognition," PhD dissertation, Cambridge University, 2003.
21. B. Raj, R. Singh, and R. Stern, "On tracking noise with linear dynamical system models," in International Conference on Acoustics, Speech and Signal Processing, Montreal, Canada, May 2004.
22. M. Riedmiller and H. Braun, "A direct adaptive method for faster backpropagation learning: The RPROP algorithm," in IEEE International Conference on Neural Networks, vol. 1, 1993, pp. 586-91.
23. B. Schuller, M.Wollmer, T. Moosmayr, and G. Rigoll, "Recognition of noisy speech: A comparative survey of robust model architecture and feature enhancement," EURASIP Journal on Audio, Speech and Music Processing, 2009.
24. V. Stouten, H. Van hamme, K. Demuynck, and P. Wambacq, "Robust speech recognition using model-based feature enhancement," in Proceedings of the 2003 Eurospeech,Geneva, Switzerland, September 2003, pp. 17-20.