Extension of uncertainty propagation to dynamic MFCCS for noise robust ASR

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

Volumn , Issue , 2014, Pages 5507-5511

  Tran, Dung T ^a,b,c   Vincent, Emmanuel ^a,b,c   Jouvet, Denis ^a,b,c  

^a INRIA   (France)

^b LORIA   (France)

^c UNIVERSITÉ DE LORRAINE   (France)

Author keywords

Automatic speech recognition; noise robustness; uncertainty handling

Indexed keywords

ACOUSTIC NOISE; COVARIANCE MATRIX; SIGNAL PROCESSING; SPEECH RECOGNITION;

AUTOMATIC SPEECH RECOGNITION; DYNAMIC FEATURES; NOISE ROBUSTNESS; NONSTATIONARY NOISE; RELATIVE ERROR RATES; SCALING COEFFICIENTS; UNCERTAINTY HANDLING; UNCERTAINTY PROPAGATION;

UNCERTAINTY ANALYSIS;

EID: 84905216197     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2014.6854656     Document Type: Conference Paper

References (25)

1. J.M. Baker, L. Deng, J. Glass, S. Khudanpur, C.-H. Lee, N. Morgan, and D. O'Shaughnessy, "Research developments and directions in speech recognition and under-standing, part 1," IEEE Signal Processing Magazine, vol. 26, no. 3, pp. 75-80, May 2009.
2. M. Wolfel and J. McDonough, Distant Speech Recognition, Wiley, 2009.
3. T. Virtanen, R. Singh, and B. Raj, Eds., Techniques for Noise Robustness in Automatic Speech Recognition, Wiley, 2012.
4. E. Vincent, J. Barker, S.Watanabe, J. Le Roux, F. Nesta, and M. Matassoni, "The second 'CHiME' speech separation and recognition challenge: An overview of challenge systems and outcomes," in Proc. ASRU, 2013.
5. M. Gales, Model Based Techniques for Noise Robust Speech Regcognition, Ph.D. thesis, Cambridge University, 1995.
6. C. Kim and R. Stern, "Power-normalized cepstral coefficients (PNCC) for robust speech recognition," in Proc. ICASSP, 2012, pp. 4101-4104.
7. L. Deng, A. Acero, M. Plumpe, and X. D. Huang, "Large vocabulary speech recognition under adverse acoustic environments," in Proc. ICSLP, 2000, pp. 806-809.
8. M. Cooke, "Robust automatic speech recognition with missing and unreliable acoustic data," Speech Communication, vol. 34, no. 3, pp. 267-285, June 2001.
9. H. Liao and M. J. F. Gales, "Adaptive training with joint uncertainty decoding for robust recognition of noisy data," in Proc. ICASSP, 2007, vol. 4, pp. 389-392.
10. M. Delcroix, T. Nakatani, and S. Watanabe, "Static and dynamic variance compensation for recognition of reverberant speech with dereverberation preprocessing," IEEE Transactions on Audio, Speech, and Language Processing, vol. 17, no. 2, pp. 324-334, Jan 2009.
11. L. Deng, "Front-end, back-end, and hybrid techniques for noise-robust speech recognition," in Robust Speech Recognition of Uncertain or Missing Data-Theory and Applications, pp. 67-99. Springer, 2011.
12. D. Kolossa, R. Astudillo, E. Hoffmann, and R. Orglmeister, "Independent component analysis and timefrequency masking for multi speaker recognition," in EURASIP Journal on Audio, Speech, and Music Processing, 2010, vol. 2010, Article ID 651420.
13. R. Astudillo and D. Kolossa, "Uncertainty propagation," in Robust Speech Recognition of Uncertain or Missing Data-Theory and Applications, D. Kolossa and R. Haeb-Umbach, Eds., pp. 35-62. Springer, 2011.
14. H. Kallasjoki, S. Keronen, G. J. Brown, J. F. Gemmeke, U. Remes, and K. J. Palomaki, "Mask estimation and sparse imputation for missing data speech recognition in multisource reverberant environments," in Proc. CHiME, 2011, pp. 58-63.
15. F. Nesta, M. Matassoni, and R. Astudillo, "A flexible spatial blind source extraction framework for robust speech recognition in noisy environments," in Proc. CHiME, 2013, pp. 33-40.
16. L. Deng, J. Wu, J. Droppo, and A. Acero, "Dynamic compensation of HMM variances using the feature enhancement uncertainty computed from a parametric model of speech distortion," IEEE Transactions on Audio, Speech, and Language Processing, vol. 13, no. 3, pp. 412-421, May 2005.
17. A. Ozerov, M. Lagrange, and E. Vincent, "Uncertaintybased learning of acoustic models from noisy data," Computer Speech and Language, vol. 27, no. 3, pp. 874-894, Feb. 2013.
18. A. Ozerov, E. Vincent, and F. Bimbot, "A general flexible framework for the handling of prior information in audio source separation," IEEE Transactions on Audio, Speech, and Language Processing, vol. 20, no. 4, pp. 1118-1133, May 2012.
19. R. Astudillo, Integration of Short-Time Fourier Domain Speech Enhancement and Observation Uncertainty Techniques for Robust Automatic Speech Recognition, Ph.D. thesis, TU Berlin, 2010.
20. I. Gradshteyn and I. Ryzhik, Table of Intergral, Series and Product, 1995.
21. S. Rice, "Mathematical analysis of random noise," Bell System Technical Journal, vol. 23, 1944.
22. P. J. Moreno, B. Raj, and R. M. Stern, "A vector Taylor series approach for environment-independent speech recognition," in Proc. ICASSP, 1996, vol. 2, pp. 733-736.
23. S. Young, G. Evermann, D. Kershaw, G. Moore, J. Odell, D. Ollason, V. Valtchev, and P. Woodland, The HTK book, 2002.
24. R. Kompass, "A generalized divergence measure fon nonnegative matrix factorization," Neural Computation, vol. 19, no. 3, pp. 780-791, Mar. 2007.
25. K. Adiloǧlu and E. Vincent, "Variational Bayesian inference for source separation and robust feature extraction," Tech. Rep. RT-0428, Inria, Aug. 2012.