MMSE-based missing-feature reconstruction with temporal modeling for robust speech recognition

IEEE Transactions on Audio, Speech and Language Processing

Volumn 21, Issue 3, 2013, Pages 624-635

  González, José A ^a   Peinado, Antonio M ^a   Ma, Ning ^b   Gómez, Angel M ^a   Barker, Jon ^c  

^a UNIVERSITY OF GRANADA   (Spain)

^b MRC INSTITUTE OF HEARING RESEARCH   (United Kingdom)

^c UNIVERSITY OF SHEFFIELD   (United Kingdom)

Author keywords

Minimum mean square error estimation; missing feature; robust speech recognition; spectral reconstruction

Indexed keywords

BASELINE SYSTEMS; FEATURE COMPENSATION; GAUSSIAN MIXTURE MODEL; LOG-SPECTRAL DOMAIN; MINIMUM MEAN SQUARE ERROR ESTIMATIONS; MISSING-FEATURE; NOISE ROBUST SPEECH RECOGNITION; NOVEL TECHNIQUES; RECOGNITION PERFORMANCE; RECONSTRUCTION TECHNIQUES; ROBUST SPEECH RECOGNITION; SEQUENTIAL STRUCTURE; SPECTRAL RECONSTRUCTION; TEMPORAL CONSTRAINTS; TEMPORAL MODELING; TIME CORRELATIONS; TIME FREQUENCY;

FREQUENCY BANDS; HIDDEN MARKOV MODELS;

SPEECH RECOGNITION;

EID: 84872188748     PISSN: 15587916     EISSN: None     Source Type: Journal    
DOI: 10.1109/TASL.2012.2229982     Document Type: Article

References (49)

1. Y. Gong, "Speech recognition in noisy environments: A survey," Speech Commun., vol. 16, no. 3, pp. 261-291, Apr. 1995.
2. 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 understanding, Part 1," IEEE Signal Process. Mag., vol. 26, no. 3, pp. 75-80, May 2009.
3. J. M. Baker, L. Deng, S. Khudanpur, C.-H. Lee, J. Glass, N. Morgan, andD.O'Shaughnessy, "UpdatedMINDS report on speech recognition and understanding, Part 2," IEEE Signal Process. Mag., vol. 26, no. 4, pp. 78-85, Jul. 2009.
4. M. Cooke, P. Green, L. Josifovski, and A. Vizinho, "Robust automatic speech recognition with missing and unreliable acoustic data," Speech Commun., vol. 34, no. 3, pp. 267-285, Jun. 2001. (Pubitemid 32284867)
5. B. Raj, M. L. Seltzer, and R. M. Stern, "Reconstruction of missing features for robust speech recognition," Speech Commun., vol. 43, no. 4, pp. 275-296, Sep. 2004.
6. H. Fletcher, Speech and Hearing in Communication. NewYork:Van Nostrand, 1953.
7. R. Warren, K. Riener, J. Bashford, and B. Brubaker, "Spectral redundancy: Intelligibility of sentences heard through narrow spectral slits," Percept. Psychophys., vol. 57, no. 2, pp. 175-182, Feb. 1995.
8. M. Cooke, "A glimpsing model of speech perception in noise," J. Acoust. Soc. Amer., vol. 119, no. 3, pp. 1562-1573, Mar. 2006. (Pubitemid 43326025)
9. A. P. Varga and R. K. Moore, "Hidden Markov model decomposition of speech and noise," in Proc. ICASSP, 1990, pp. 845-848.
10. J. Barker, L. Josifovski, M. P. Cooke, and P. D. Green, "Soft decisions in missing data techniques for robust automatic speech recognition," in Proc. ICSLP, 2000, pp. 373-376.
11. N. Ma, P. Green, J. Barker, and A. Coy, "Exploiting correlogram structure for robust speech recognition with multiple speech sources," Speech Commun., vol. 49, no. 12, pp. 874-891, Dec. 2007. (Pubitemid 47488511)
12. J. A. Morales-Cordovilla, N. Ma, V. E. Sanchez, J. L. Carmona, A. M. Peinado, and J. Barker, "A pitch based noise estimation technique for robust speech recognition with missing data," in Proc. ICASSP, 2011, pp. 4808-4811.
13. M. L. Seltzer, B. Raj, and R. M. Stern, "A bayesian classifier for spectrographic mask estimation for missing feature speech recognition," Speech Commun., vol. 43, no. 4, pp. 379-393, Sep. 2004.
14. B. J. Borgström and A. Alwan, "A statistical approach to Mel-domain mask estimation for missing-feature ASR," IEEE Signal Process. Lett., vol. 17, no. 11, pp. 941-944, Nov. 2010.
15. W. Kim and R. M. Stern, "Mask classification for missing-feature reconstruction for robust speech recognition in unknown background noise," Speech Commun., vol. 53, no. 1, pp. 1-11, Jan. 2011.
16. S. Badiezadegan and R. C. Rose, "Mask estimation in non-stationary noise environments for missing feature based robust speech recognition," in Proc. Interspeech, 2010, pp. 2062-2065.
17. C. Cerisara, S. Demange, and J.-P. Haton, "On noise masking for automatic missing data speech recognition: A survey and discussion," Comput. Speech Lang., vol. 21, no. 3, pp. 443-457, July 2007. (Pubitemid 46367508)
18. J. Barker,M. Cooke, and D. Ellis, "Decoding speech in the presence of other sources," Speech Commun., vol. 45, no. 1, pp. 5-25, Jan. 2005. (Pubitemid 40034706)
19. N. Ma, J. Barker, H. Christensen, and P. Green, "Combining speech fragment decoding and adaptive noise floor modelling," IEEE Trans. Audio Speech Lang. Process., vol. 20, no. 3, pp. 818-827, Mar. 2012.
20. H. Van Hamme, "PROSPECT features and their application to missing data techniques for robust speech recognition," in Proc. Interspeech, 2004, pp. 101-104.
21. M. Van Segbroeck and H. Van Hamme, "Advances in missing feature techniques for robust large-vocabulary continuous speech recognition," IEEE Trans. Audio Speech Lang. Process., vol. 19, no. 1, pp. 123-137, Jan. 2011.
22. W. Kim and J. Hansen, "Missing-feature reconstruction by leveraging temporal spectral correlation for robust speech recognition in background noise conditions," IEEE Trans. Audio Speech Lang. Process., vol. 18, no. 8, pp. 2111-2120, Nov. 2010.
23. B. Raj and R. Singh, "Reconstructing spectral vectors with uncertain spectrographic masks for robust speech recognition," in Proc. ASRU, 2005, pp. 65-70.
24. J. F. Gemmeke, H. Van Hamme, B. Cranen, and L. Boves, "Compressive sensing for missing data imputation in noise robust speech recognition," IEEE J. Sel. Topics Signal Process., vol. 4, no. 2, pp. 272-287, Apr. 2010.
25. F. Faubel, H. Raja, J. McDonough, and D. Klakow, "Particle filter based soft-mask estimation for missing feature reconstruction," in Proc. IWAENC, 2008.
26. F. Faubel, J. McDonough, and D. Klakow, "Bounded conditionalmean imputation with Gaussian mixture models: A reconstruction approach to partly occluded features," in Proc. ICASSP, 2009, pp. 3869-3872.
27. J. A. González, A. M. Peinado, A. M. Gómez, N. Ma, and J. Barker, "Combining missing-data reconstruction and uncertainty decoding for robust speech recognition," in Proc. ICASSP, 2012, pp. 4693-4696.
28. A. M. Peinado, V. Sanchez, J. L. Perez-Cordoba, and A. de la Torre, "HMM-based channel error mitigation and its application to distributed speech recognition," Speech Commun., vol. 41, no. 4, pp. 549-561, Nov. 2003.
29. J. A. González, A. M. Peinado, A. M. Gomez, and J. L. Carmona, "EfficientMMSE estimation and uncertainty processing for multienvironment robust speech recognition," IEEE Trans. Audio Speech Lang. Process., vol. 19, no. 5, pp. 1206-1220, Jul. 2011.
30. J. L. Carmona, A. M. Peinado, J. L. Perez-Cordoba, and A.M. Gomez, "MMSE-based packet loss concealment forCELP-coded speech recognition," IEEE Trans. Audio Speech Lang. Process., vol. 18, no. 6, pp. 1341-1353, Aug. 2010.
31. B. J. Borgström and A. Alwan, "HMM-based reconstruction of unreliable spectrographic data for noise robust speech recognition," IEEE Trans. Audio Speech Lang. Process., vol. 18, no. 6, pp. 1612-1623, Aug. 2010.
32. 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 Trans. Speech Audio Process., vol. 12, no. 3, pp. 218-233, May 2004.
33. P. Moreno, "Speech recognition in noisy environments," Ph.D. dissertation, Dept. of Elect. and Comput. Eng., Carnegie Mellon Univ., Pittsburgh, PA, 1996.
34. A. Acero, Acoustical and Environmental Robustness in Automatic Speech Recognition. Norwell, MA: Kluwer, 1993.
35. V. Stouten, H. V. Hamme, and P.Wambacq, "Model-based feature enhancement with uncertainty decoding for noise robust ASR," Speech Commun., vol. 48, no. 11, pp. 1502-1514, Nov. 2006. (Pubitemid 44634766)
36. S. T. Roweis, "One microphone source separation," in Proc. Neuroal Inf. Process. Syst., 2001, pp. 793-799.
37. S. T. Roweis, "Factorial models and refiltering for speech separation and denoising," in Proc. EUROSPEECH, 2003, pp. 1009-1012.
38. S. J. Rennie, J. R. Hershey, and P. A. Olsen, "Single-channel multitalker speech recognition," IEEE Signal Process. Mag., vol. 27, no. 6, pp. 66-80, Nov. 2010.
39. A. Genz, "Numerical computation of multivariate normal probabilities," J. Comput. Graph. Stat., vol. 1, no. 2, pp. 141-149, Jun. 1992.
40. F. Seide and P. Zhao, "On using missing-feature theory with cepstral features-Approximations to the multivariate integral," in Proc. Interspeech, 2010, pp. 2094-2097.
41. J. A. González, A.M. Peinado,A. M. Gómez, andN.Ma, "Log-spectral feature reconstruction based on an occlusion model for noise robust speech recognition," in Proc. Interspeech, 2012.
42. H. G. Hirsch and D. Pearce, "The Aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions," in Proc. ICSLP, 2000, pp. 29-32.
43. I. T. Jolliffe, Principal Component Analysis. NewYork:Springer-Verlag, 2002.
44. L. Rabiner, "A tutorial on hidden Markov models and selected applications in speech recognition," Proc. IEEE, vol. 77, no. 2, pp. 257-286, Feb. 1989.
45. H. G. Hirsch, "Experimental framework for the performance evaluation of speech recognition front-ends of large vocabulary task," AURORA DSR Working Group, Tech. Rep., STQ, 2002.
46. ETSI ES 201 108-Distributed Speech Recognition; Front-End Feature Extraction Algorithm; Compression Algorithms, Std., 2000.
47. T. H. Crystal and A. S. House, "Segmental durations in connectedspeech signals: Current results," J. Acoust. Soc. Amer., vol. 83, no. 4, pp. 1553-1573, Apr. 1988.
48. Speech Processing, Transmission and Quality Aspects (STQ); Distributed speech recognition; Advanced front-end feature extraction algorithm; Compression algorithms, ETSI 202 050 v1.1.4 Std., Nov. 2005.
49. N. L. Johnson, S. Kotz, and N. Balakrishnan, Continuous Univariate Distributions. New York: Wiley, 1994, vol. 1.