Computing MMSE estimates and residual uncertainty directly in the feature domain of ASR using STFT domain speech distortion models

IEEE Transactions on Audio, Speech and Language Processing

Volumn 21, Issue 5, 2013, Pages 1023-1034

  Astudillo, Ramón Fernández ^a   Orglmeister, Reinhold ^b  

^a INESC   (Portugal)

^b TECHNISCHE UNIVERSITÄT BERLIN   (Germany)

Author keywords

MMSE; uncertainty decoding; uncertainty propagation; wiener filter

Indexed keywords

AUTOMATIC SPEECH RECOGNITION; CEPSTRAL COEFFICIENTS; DISTORTION MODEL; DYNAMIC COMPENSATION; FEATURE DOMAIN; FEATURE EXTRACTION METHODS; MINIMUM MEAN SQUARE ERRORS (MMSE); MMSE; MMSE ESTIMATORS; OBSERVATION UNCERTAINTIES; POSTERIOR DISTRIBUTIONS; ROBUST ASR; SHORT TIME FOURIER TRANSFORMS; SPEECH DISTORTION; UNCERTAINTY DECODING; UNCERTAINTY PROPAGATION; WIENER FILTERS;

FEATURE EXTRACTION; SPEECH RECOGNITION; UNCERTAINTY ANALYSIS;

ESTIMATION;

EID: 84873901811     PISSN: 15587916     EISSN: None     Source Type: Journal    
DOI: 10.1109/TASL.2013.2244085     Document Type: Article

References (49)

1. Speech Processing, Transmission and Quality Aspects (STQ); Dis tributed Speech recognition; Front-end feature extraction algorithm; Compression algorithms, ETSI ES 202 050 v1.1.5 (2007-01, ETSI, Jan. 2007.
2. M. J. F. Gales, "Model-based technique for noise robust speech recognition," Ph.D. dissertation, Gonville and Caius College, Cambridge, U.K., 1995.
3. J. Arrowood and M. Clements, "Using observation uncertainty in HMM decoding," in Proc. Int. Conf. Spoken Lang. Process. (ICSLP), 2002.
4. T. T. Kristjansson and B. J. Frey, "Accounting for uncertainty in observations: A new paradigm for robust automatic speech recognition," Probabilistic and Statistical Inference Group, University of Toronto, 2002, Tech. Rep.
5. J. Droppo, A. Acero, and L. Deng, "Uncertainty decoding with splice for noise robust speech recognition," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP)., 2002, vol. 1, pp. I-57-I-60, vol.1.
6. L. Deng, J. Droppo, and A. Acero, "Exploiting variances in robust feature extraction based on a parametric model of speech distortion," in Proc. Int. Conf. Spoken Lang. Process. (ICSLP), 2002.
7. D. Kolossa, A. Klimas, and R. Orglmeister, "Separation and robust recognition of noisy, convolutive speech mixtures using time-frequency masking and missing data techniques," in Proc. Workshop Applicat. Signal Process. Audio Acoust. (WASPAA), Oct. 2005, pp. 82-85.
8. H. Liao and M. Gales, "Issues with uncertainty decoding for noise robust automatic speech recognition," Speech Commun., vol. 50, no. 4, pp. 265-277, 2008.
9. D. Kolossa and R. Haeb-Umbach, Eds., Robust Speech Recognition of Uncertain or Missing Data-Theory and Applications. New York, NY, USA: Springer, 2011.
10. A. Ozerov, M. Lagrange, and E. Vincent, "GMM-based classification from noisy features," in Proc. 1st Int. Workshop Mach. Listening in Multisource Environ. (CHiME), 2011, pp. 30-35.
11. A. Krueger and R. Haeb-Umbach, "Model based feature enhancement for automatic speech recognition in reverberant environments," in In Proc. Interspeech, 2009, pp. 1231-1234.
12. N. Yoma and M. Villar, "Speaker verification in noise using a stochastic version of the weighted viterbi algorithm," IEEE Trans. Speech Audio Process., vol. 10, no. 3, pp. 158-166, Mar. 2002.
13. S. Srinivasan and D. Wang, "A supervised learning approach to uncertainty decoding for robust speech recognition," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), vol. 1, pp. I-I, 14-19 2006.
14. S. Srinivasan and D. Wang, "Transforming binary uncertainties for robust speech recognition," IEEE Trans. Audio, Speech, Lang. Process., vol. 15, no. 7, pp. 2130-2140, Sep. 2007.
15. R. F. Astudillo, A. Abad, and J. P. Neto, "Integration of beamforming and automatic speech recognition through propagation of the wiener posterior," in Proc. ICASSP, Apr. 2012, pp. 4909-4912.
16. D. Kolossa, R. F. Astudillo, E. Hoffmann, and R. Orglmeister, "Independent component analysis and time-frequency masking for speech recognition in multi-talker conditions," EURASIP J. Audio, Speech, Music Process., pp. 1-13, 2010.
17. R. F. Astudillo, D. Kolossa, P. Mandelartz, and R. Orglmeister, "An uncertainty propagation approach to robust ASR using the ETSI advanced front-end," IEEE J. Sel. Topics Signal Process., vol. 4, no. 5, pp. 824-833, Oct. 2010.
18. R. F. Astudillo and R. Orglmeister, "A MMSE estimator in mel-cep-stral domain for robust large vocabulary automatic speech recognition using uncertainty propagation," in Proc. Interspeech, 2010.
19. D. Yu, L. Deng, J. Droppo, J. Wu, Y. Gong, and A. Acero, "Robust speech recognition using a cepstral minimum-mean-square-error-motivated noise suppressor," IEEE Trans. Audio, Speech, Lang. Process., vol. 16, no. 5, pp. 1061-1070, Jul. 2008.
20. A. Stark and K. Paliwal, "MMSE estimation of log-filterbank energies for robust speech recognition," Speech Commun., vol. 53, no. 3, pp. 403-416, 2011.
21. V. Ion and R. Haeb-Umbach, "Improved source modeling and predictive classification for channel robust speech recognition," in Proc. Interspeech, 2006.
22. R. McAulay and M. Malpass, "Speech enhancement using a soft-decision noise suppression filter," IEEE Trans. Acoust., Speech, Signal Process., vol. ASSP-28, no. 2, pp. 137-145, Apr. 1980.
23. Y. Ephraim and D. Malah, "Speech enhancement using a minimum-mean square error short-time spectral amplitude estimator," IEEE Trans. Acoust., Speech, Signal Process., vol. ASSP-32, no. 6, pp. 1109-1121, Dec. 1984.
24. Y. Ephraim and D. Malah, "Speech enhancement using a minimum mean square error log-spectral amplitude estimator," IEEE Trans. Acoust., Speech, Signal Process., vol. ASSP-33, no. 2, pp. 443-445, Apr. 1985.
25. E. A. P. Habets, "Single-and multi-microphone speech dereverbera-tion using spectral enhancement," Ph.D. dissertation, Technische Univ. Eindhoven, Eindhoven, The Netherlands, 2007.
26. R. Zelinski, "A microphone array with adaptive post-filtering for noise reduction in reverberant rooms," in Proc. Int. Conf. Acoust., Speech, Signal Process., Apr. 1988, vol. 5, pp. 2578-2581.
27. S. Gannot and I. Cohen, "Speech enhancement based on the general transfer function GSC and postfiltering," IEEE Trans. Speech Audio Process., vol. 12, no. 6, pp. 561-571, Nov. 2004.
28. F. Nesta and M. Matassoni, "Robust automatic speech recognition through on-line semi blind source extraction," in Proc. Int. Workshop Mach. Listening in Multisource Environ., 2011, pp. 18-23.
29. I. Cohen, "Noise spectrum estimation in adverse environments: Improved minima controlled recursive averaging," IEEE Trans. Speech Audio Process., vol. 11, no. 5, pp. 466-475, Sept. 2003.
30. S. M. Kay, Fundamentals of Statistical Signal Processing, ser. Signal Processing Series. Englewood Cliffs, NJ, USA: Prentice-Hall, 1993.
31. R. F. Astudillo, D. Kolossa, and R. Orglmeister, "Accounting for the uncertainty of speech estimates in the complex domain for minimum mean square error speech enhancement," in Proc. Interspeech, 2009.
32. I. S. Gradshteyn and I. Ryzhik, Table of Integrals. Amsterdam, The Netherlands: Elsevier, 2007.
33. I. Andrianakis and P. White, "MMSE speech spectral amplitude estimators with chi and gamma speech priors," in Proc. IEEE Int. Conf. Acoust., Speech Signal Process. (ICASSP), May 2006, vol. 3, pp. III-1068-III-1071.
34. J. Erkelens, R. Hendriks, R. Heusdens, and J. Jensen, "Minimum mean-square error estimation of discrete fourier coefficients with generalized gamma priors," IEEE Trans. Audio, Speech, Lang. Process., vol. 15, no. 6, pp. 1741-1752, Aug. 2007.
35. P. J. Wolfe and S. J. Godsill, "Efficient alternatives to the ephraim and malah suppression rule for audio signal enhancement," EURASIP J. Appl. Signal Process., vol. 10, pp. 1043-1051, 2003.
36. R. F. Astudillo, "Integration of short-time Fourier domain speech enhancement and observation uncertainty techniques for robust automatic speech recognition," Ph.D. dissertation, Technische Univ. Berlin, Berlin, Germany, 2010.
37. R. F. Astudillo, D. Kolossa, and R. Orglmeister, "Propagation of statistical information through non-linear feature extractions for robust speech recognition," in Proc. MaxEnt2007, 2007.
38. R. F. Astudillo, D. Kolossa, and R. Orglmeister, "Uncertainty propagation for speech recognition using rasta features in highly nonstationary noisy environments," in Proc. ITG Workshop for Speech Commun., 2008.
39. R. F. Astudillo and J. P. Neto, "Propagation of uncertainty through multilayer perceptrons for robust automatic speech recognition," in Proc. Interspeech, 2011, pp. 461-464.
40. S. Chakraborty, "Some applications of dirac's delta function in statistics for more than one random variable," Applicat. Appl. Math., vol. 3, no. 1, pp. 42-54, 2008.
41. S. Julier and J. Uhlmann, A general method for approximating nonlinear transformations of probability distributions Univ. of Oxford, Oxford, U.K., 1996, Tech. Rep.
42. L. Fenton, "The sum of log-normal probability distributions in scattered transmission systems," IRE Trans. Commun. Syst., vol. 8, pp. 57-67, 1960.
43. B. Frey, L. Deng, A. Acero, and T. T. Kristjansson, "Iterating Laplaces method to remove multiple types of acoustic distortion for robust speech recognition," in Proc. Eurospeech, Aalborg, Denmark, Sep. 2001.
44. H. Liao and M. J. F. Gales, "Joint uncertainty decoding for noise robust speech recognition," in Proc. Interspeech, 2005, pp. 3129-3132.
45. B. Raj and R. Stern, "Missing-feature approaches in speech recognition," IEEE Signal Process. Mag., vol. 22, no. 5, pp. 101-116, Sep. 2005.
46. G. Hirsch, Experimental framework for the performance evaluation of speech recognition front-ends on a large vocabulary task Germany, Niederrhein Univ. of Appl. Sci., Nov. 2002.
47. S. Young, The HTK Book (for HTK Version 3.4). Cambridge, U.K.: Cambridge Univ. Engineering Department., 2006.
48. K. Vertanen, HTK Wall Street Journal Training recipe, 2006 [Online]. Available: http://www.inference.phy.cam.ac.uk/kv227/htk/
49. R. F. Astudillo, Aurora4 benchmark for stft-up, 2013 [Online]. Available: http://www.astudillo.com/ramon/research/stft-up/