Missing-Data Techniques: Recognition with Incomplete Spectrograms

Techniques for Noise Robustness in Automatic Speech Recognition

Volumn , Issue , 2012, Pages 369-398

  Barker, Jon ^a  

^a UNIVERSITY OF SHEFFIELD   (United Kingdom)

Author keywords

Energetic masking, and MAR validity in speech processing data loss; Information loss compensation; Missing data approaches in theoretical framework; Missing data classification, or missing data mask segmentation; Missing data imputation; Missing data masks and mask uncertainty, using fragment decoding; Missing data technique, incomplete spectrograms and recognition; Noise masker opaque effectiveness, signal perception consistency; Noise robust speech recognition, of speech in incomplete spectrograms; Robust ASR problems, information loss than in model mismatch

Indexed keywords

EID: 84880535669     PISSN: None     EISSN: None     Source Type: Book    
DOI: 10.1002/9781118392683.ch14     Document Type: Chapter

References (37)

1. S. Ahmad and V. Tresp, "Some solutions to the missing feature problem in vision," Advances in Neural Information Processing Systems, vol. 5, pp. 393-400, 1993.
2. J. Barker, L. Josifovski, M. Cooke, and P. Green, "Soft decisions in missing data techniques for robust automatic speech recognition," in Sixth International Conference on Spoken Language Processing, 2000.
3. J. Barker,M. Cooke, and D. Ellis, "Decoding speech in the presence of other sources," Speech Communication, vol. 45, no. 1, pp. 5-25, 2005.
4. H. Bourlard and S. Dupont, "Subband-based speech recognition," in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP-97), vol. 2. IEEE, 1997, pp. 1251-1254.
5. A. Bregman, Auditory scene analysis. Cambridge, MA: MIT press, 1990.
6. H. Christensen, N. Ma, S. Wrigley, and J. Barker, "A speech fragment approach to localising multiple speakers in reverberant environments," in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2009), IEEE, 2009, pp. 4593-4596.
7. M. Cooke and Y. Lu, "Spectral and temporal changes to speech produced in the presence of energetic and informational maskers," The Journal of the Acoustical Society of America, vol. 128, pp. 2059-2069, 2010.
8. M. Cooke, P. Green, and M. Crawford, "Handling missing data in speech recognition," in Proceeding of the International Conference on Spoken Language Processing, 1994, pp. 1555-1558.
9. M. Cooke, P. Green, L. Josifovski, and A. Vizinho, "Robust automatic speech recognition with missing and unreliable acoustic data," Speech communication, vol. 34, no. 3, pp. 267-285, 2001.
10. M. Cooke, J. Hershey, and S. Rennie, "Monaural speech separation and recognition challenge," Computer Speech & Language, vol. 24, pp. 1-15, 2010.
11. S. Demange, C. Cerisara, and J.-P. Haton, "A speech fragment approach to localising multiple speakers in reverberant environments," in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2006), IEEE, 2006.
12. A. Dempster et al., "Maximum likelihood from incomplete data via the EM algorithm," Journal of the Royal Statistical Society. Series B (Methodological), vol. 39, no. 1, pp. 1-38, 1977.
13. J. Droppo, A. Acero, and L. Deng, "Uncertainty decoding with splice for noise robust speech recognition," in IEEE International Conference on Acoustics Speech and Signal Processing, vol. 1. IEEE; 1999, 2002.
14. F. Faubel, J. McDonough, and D. Klakow, "Bounded conditional mean imputation with Gaussian mixture models: a reconstruction approach to partly occluded features," in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2009), IEEE, 2009, pp. 3869-3872.
15. B. Gold, N. Morgan, and D. Ellis, Speech and Audio Signal Processing: Processing and Perception of Speech and Music, 2nd ed. Hoboken, NJ, USA: John Wiley & Sons, Inc., 2011.
16. D. Heitjan and S. Basu, "Distinguishing 'Missing At Random' and 'Missing Completely At Random'," The American Statistician, vol. 50, no. 3, pp. 207-213, 1996.
17. E. Lombard, "Le signe de lelevation de la voix," Annales Des Maladies Oreille, Larynx, Nez, Pharynx, vol. 37, no. 101-119, p. 25, 1911.
18. N. Ma, P. Green, J. Barker, and A. Coy, "Exploiting correlogram structure for robust speech recognition with multiple speech sources," Speech Communication, vol. 49, no. 12, pp. 874-891, 2007.
19. P. Mermelstein and S. Davis, "Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences," IEEE Transactions on Acoustics, Speech and Signal Processing, vol. 28, no. 4, p. 357, 1980.
20. J. Ming and F. Jack Smith, "Union: a model for partial temporal corruption of speech," Computer Speech & Language, vol. 15, no. 3, pp. 217-231, 2001.
21. J. Ming and F. Jack Smith, "Speech recognition with unknown partial feature corruption-a review of the union model," Computer Speech & Language, vol. 17, no. 2-3, pp. 287-305, 2003.
22. J. Ming and F. Smith, "Union: A new approach for combining sub-band observations for noisy speech recognition," Speech Communication, vol. 34, no. 1-2, pp. 41-55, 2001.
23. J. Ming and F. Smith, "A posterior union model for improved robust speech recognition in nonstationary noise," in IEEE International Conference on Acoustics, Speech and Signal Processing, (ICASSP'03), vol. 1. IEEE, 2003.
24. A. Morris, A. Hagen, and H. Bourlard, "The full combination sub-bands approach to noise robust HMM/ANN based ASR," in Sixth European Conference on Speech Communication and Technology, 1999.
25. A. Morris, J. Barker, and H. Bourlard, "From missing data to maybe useful data: soft data modelling for noise robust ASR," in Proceedings of WISP. Stratford-upon-Avon, UK: Citeseer, 2001.
26. D. Morrison, Multivariate Statistical Methods, 3rd ed. McGraw-Hill, 1990.
27. A. Potamianos and V. Weerackody, "Soft-feature decoding for speech recognition over wireless channels," in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP'01), vol. 1. IEEE, 2002, pp. 269-272.
28. B. Raj and R. Stern, "Missing-feature approaches in speech recognition," IEEE Signal Processing Magazine, vol. 22, pp. 101-116, 2005.
29. B. Raj, M. Seltzer, and R. Stern, "Reconstruction of missing features for robust speech recognition," Speech Communication, vol. 43, no. 4, pp. 275-296, 2004.
30. D. Rubin, "Inference and missing data," Biometrika, vol. 63, no. 3, p. 581, 1976.
31. J. Schafer, Analysis of incomplete multivariate data. Boca Raton, FL, USA: Chapman & Hall/CRC, 1997.
32. M. Seltzer, B. Raj, and R. Stern, "A Bayesian classifier for spec-trographic mask estimation for missing feature speech recognition," Speech Communication, vol. 43, no. 4, pp. 379-393, 2004.
33. Z. Tan, P. Dalsgaard, and B. Lindberg, "Automatic speech recognition over error-prone wireless networks," Speech Communication, vol. 47, no. 1-2, pp. 220-242, 2005.
34. H. van Hamme, "Handling time-derivative features in a missing data framework for robust automatic speech recognition," in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2006), vol. 1. IEEE, 2006.
35. M. van Segbroeck and H. van Hamme, "Vector-quantization based mask estimation for missing data automatic speech recognition," in Proceedings of Interspeech, Antwerp, Belgium, 2007.
36. R.Weiss andD. Ellis, "Estimating single-channel source separation masks: Relevance vector machine classifiers vs. pitch-based masking," in Proceedings of the ISCA Tutorial and ResearchWorkshop on Statistical Perceptual Audition (SAPA), Pittsburgh, PA, 2006, pp. 31-36.
37. D. Williams, X. Liao, Y. Xue, L. Carin, and B. Krishnapuram, "On classification with incomplete data," IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 427-436, 2007.