Compressive sensing for missing data imputation in noise robust speech recognition

IEEE Journal on Selected Topics in Signal Processing

Volumn 4, Issue 2, 2010, Pages 272-287

  Gemmeke, Jort Florent ^a   Van Hamme, Hugo ^b   Cranen, Bert ^a   Boves, Lou ^a  

^a RADBOUD UNIVERSITY NIJMEGEN   (Netherlands)

^b UNIVERSITY OF LEUVEN   (Belgium)

Author keywords

Automatic speech recognition (ASR); Compressive sensing (CS); Missing data techniques; Noise robustness

Indexed keywords

A-FRAMES; AUTOMATIC SPEECH RECOGNITION; CLEAN SPEECH; CONVENTIONAL TECHNIQUES; ERROR PRONES; IMPUTATION TECHNIQUES; LINEAR COMBINATIONS; LOW SIGNAL-TO-NOISE RATIO; MISSING DATA; MISSING DATA TECHNIQUES; NOISE ROBUST SPEECH RECOGNITION; NOISE ROBUSTNESS; NOISY OBSERVATIONS; NOISY SPEECH; NON-PARAMETRIC; OVERCOMPLETE DICTIONARIES; PARAMETRIC MODELS; TIME FRAME; TIME WINDOWS;

ACOUSTIC NOISE; CHANNEL ESTIMATION; REMELTING; SIGNAL RECONSTRUCTION; SIGNAL TO NOISE RATIO;

SPEECH RECOGNITION;

EID: 77949695902     PISSN: 19324553     EISSN: None     Source Type: Journal    
DOI: 10.1109/JSTSP.2009.2039171     Document Type: Article

References (55)

1. S. Ahmad and V. Tresp, "Some solutions to the missing feature problem in vision," in Advances in Neural Information Processing Systems 5, S. Hanson, J. Cowan, and C. Giles, Eds. San Franciso, CA: Morgan Kaufmann, 1993, pp. 393-400.
2. R. Duda and P. Hart, Pattern Classification and Scene Analysis. New York: Wiley, 1973.
3. B. Raj, R. Singh, and R. Stern, "Inference of missing spectrographic features for robust automatic speech recognition," in Proc. Inf Conf. Spoken Lang. Process., 1998, pp. 1491-1494.
4. M. Cooke, P. Green, L. Josifovksi, and A. Vizinho, "Robust automatic speech recognition with missing and unreliable acoustic data," Speech Commun., vol.34, pp. 267-285, 2001.
5. B. Raj and R. M. Stern, "Missing-feature approaches in speech recognition," Signal Process. Mag. , vol.22, no.5, pp. 101-116, Sep. 2005.
6. B. Raj, "Reconstruction of incomplete spectrograms for robust speech recognition," Ph.D. dissertation, Carnegie Mellon Univ., Pittsburgh, PA, 2000.
7. B. Raj, M. Seltzer, and R. Stern, "Reconstruction of missing features for robust speech recognition," Speech Commun., vol.43, pp. 275-296, 2004.
8. D. L. Donoho, "Compressed sensing," IEEE Trans. Inf. Theory, vol.52, no.4, pp. 1289-1306, Apr. 2006.
9. E. J. Candès, J. Romberg, and T. Tao, "Stable signal recovery from incomplete and inaccurate measurements," Commun. Pure Appl. Math., vol.59, no.8, pp. 1207-1223, 2006.
10. Y. Zhang, When is missing data recoverable? Rice Univ., Houston, TX, CAAM Tech. Rep. TR06-15, 2006.
11. J. Wright, A. Y. Yang, A. Ganesh, S. S. Sastry, and Y. Ma, "Robust face recognition via sparse representation," IEEE Trans. Pattern Anal. Mach. Intell., vol.31, no.2, pp. 210-227, Feb. 2009.
12. H. Hirsch and D. Pearce, "The aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions," in Proc. ISCA ASR2000 Workshop, Paris, France, 2000, pp. 181-188.
13. H. Van Hamme, "Robust speech recognition using cepstral domain missing data techniques and noisy masks," in Proc. IEEE ICASSP, 2004, vol.1, pp. 213-216.
14. J.-C. Junqua and J.-P. Haton, Robustness in Automatic Speech Recognition: Fundamentals and Applications. Norwell, MA: Kluwer, 1996.
15. J. Barker,M. Cooke, and D. Ellis, "Decoding speech in the presence of other sources," Speech Commun., vol.45, pp. 5-25, 2005.
16. A. Nadas, D. Nahamoo, and M. Picheny, "Speech recognition using noise-adaptive prototypes," IEEE Trans. Acoust., Speech, Signal Process., vol.37, no.10, pp. 1495-1503, Oct. 1989.
17. A. Vizinho, P. Green, M. Cooke, and L. Josifovski, "Missing data theory, spectral subtraction and signal-to-noise estimation for robust asr: An integrated study," in Proc. Interspeech'99, 1999, pp. 2407-2410.
18. M. Seltzer, B. Raj, and R. Stern, "A bayesian classifier for spectrographic mask estimation for missing feature speech recognition," Speech Commun., vol.43, pp. 379-393, 2004.
19. W. Kim and R. M. Stern, "Band-independent mask estimation for missing-feature reconstruction in the presence of unknown background noise," in Proc. IEEE ICASSP, 2006, pp. 305-308.
20. S. Harding, J. Barker, and G. J. Brown, "Mask estimation for missing data speech recognition based on statistics of binaural interaction," IEEE Trans. Audio, Speech, Lang. Process., vol.14, no.1, pp. 58-67, Jan. 2006.
21. 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, 2007.
22. 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, 2007.
23. J. Barker, M. Cooke, and P. Green, "Robust asr based on clean speech models: An evaluation of missing data techniques for connected digit recognition in noise," in Proc. Eurospeech, 2001.
24. J. Gemmeke and B. Cranen, "Using sparse representations for missing data imputation in noise robust speech recognition," in Proc. EUSIPCO 2008, 2008.
25. B. K. Natarajan, "Sparse approximate solutions to linear systems," SIAM J. Comput., vol.24, no.2, pp. 227-234, 1995.
26. D. L. Donoho, "For most large underdetermined systems of linear equations the minimal l1-norm solution is also the sparsest solution," Commun. Pure Appl. Math., vol.59, no.6, pp. 797-829, 2006.
27. R. Tibshirani, "Regression shrinkage and selection via the lasso," J. R. Statist. Soc. Ser. B (Methodological), vol.58, no.1, pp. 267-288, 1996.
28. D. L. Donoho and J. Tanner, "Counting faces of randomly projected polytopes when the projection radically lowers dimension," [Online]. Available: http://www.math.utah.edu/tanner/ 2007
29. E. J. Candès and T. Tao, "Decoding by linear programming," IEEE Trans. Inf. Theory, vol.51, no.12, pp. 4203-4215, Dec. 2005.
30. E. J. Candès and J. Romberg, "Sparsity and incoherence in compressive sampling," Inverse Problems vol.23, no.3, pp. 969-985, Jun. 2007 [Online].Available: http://www.acm.caltech.edu/emmanuel/papers/ PartialMeasurements.pdf
31. W. Johnson and J. Lindenstrauss, "Extensions of Lipschitz embeddings into a Hilbert space," Contemporary Math., vol.26, no.10, pp. 189-206, 1984.
32. H. Van Hamme, "Prospect features and their application to missing data techniques for robust speech recognition," in Proc. Interspeech-04, 2004, pp. 101-104.
33. H. Van Hamme, "Handling time-derivative features in a missing data framework for robust automatic speech recognition," in Proc. IEEE ICASSP, 2006, pp. 293-296.
34. M. V. Segbroeck and H. Van Hamme, "Robust speech recognition using missing data techniqies in the prospect domain and fuzzy masks," in Proc. IEEE ICASSP, 2008, pp. 4393-4396.
35. S.-J. Kim, K. Koh, M. Lustig, S. Boyd, and D. Gorinevsky, "An interior-point method for large-scale l1-regularized least squares," IEEE J. Sel. Topics Signal Process., vol.1, no.4, pp. 606-617, Dec. 2007.
36. F. Sha, L. K. Saul, and D. D. Lee, "Multiplicative updates for nonnegative quadratic programming in support vector machines," in Advances in Neural Information Processing Systems 15. Cambridge, MA: MIT Press, 2002, pp. 1041-1048.
37. M. Van Segbroeck and H. Van Hamme, "Vector-Quantization based mask estimation for missing data automatic speech recognition," in Proc. ICSLP, Antwerp, Belgium, Aug. 2007, pp. 910-913.
38. J. F. Gemmeke, Y. Wang, M. V. Segbroeck, B. Cranen, and H. Van Hamme, "Application of noise robust MDT speech recognition on the SPEECON and SpeechDat-Car databases," in Proc. Interspeech-09, 2009, pp. 1227-1230.
39. M. Cooke and O. Scharenborg, "The interspeech 2008 consonant challenge," in Proc. Interspeech-08, 2008.
40. J. Gemmeke and B. Cranen, "Noise reduction through compressed sensing," in Proc. Interspeech-08, 2008.
41. J. Gemmeke and B. Cranen, "Missing data imputation using compressive sensing techniques for connected digit recognition," in Proc. DSP-09, 2009.
42. S. Rao, R. Tron, R. Vidal, and Y. Ma, "Motion segmentation via robust subspace separation in the presence of outlying, incomplete, or corrupted trajectories," in Proc. IEEE Inf Conf. Comput. Vis. Pattern Recognition, 2008, pp. 1-8.
43. M. Elad, J.-L. Starck, D. Donoho, and P. Querre, "Simultaneous cartoon and texture image inpainting using morphological component analysis (mca)," J. Appl. Comput. Harmonic Anal., vol.19, pp. 340-358, Nov. 2005.
44. M. Fadili, J.-L. Starck, and F. Murtagh, "Inpainting and zooming using sparse representations," Comput. J., vol.52, no.1, pp. 64-79, 2009.
45. M. N. Schmidt and R. K. Olsson, "Linear regression on sparse features for single-channel speech separation," in Proc. IEEE Workshop Applicat. Signal Process. Audio Acoust., (WASPAA), 2007, pp. 26-29.
46. M. E. D. T. Blumensath, "Compressed sensing and source separation," in Proc. Inf Conf. Ind. Compon. Anal. Signal Separation, Sep. 2007.
47. M. V. S. Shashanka, B. Raj, and P. Smaragdis, "Sparse overcomplete decomposition for single channel speaker separation," in Proc. IEEE ICASSP, 2007, pp. 641-644.
48. A. Coy and J. Barker, "An automatic speech recognition system based on the scene analysis account of auditory perception," Speech Commun., vol.49, no.5, pp. 384-401, 2007.
49. W. Jansen and H. Van Hamme, "Prospect features and their application to missing data techniques for vocal tract length normalization," in Proc. Interspeech-05, 2005, pp. 2753-2756.
50. J. Barker, L. Josifovski, M. Cooke, and P. Green, "Soft decisions in missing data techniques for robust automatic speech recognition," in Proc. ICSLP-00, 2000, pp. 373-376.
51. J. Gemmeke and B. Cranen, "Sparse imputation for noise robust speech recognition using soft masks," in Proc. IEEE ICASSP, 2009, pp. 4645-4648.
52. 1-minimization," IEEE Trans. Inf. Theory 2009 [Online]. Available: http://perception. csl.uiuc.edu/jnwright/, submitted for publication
53. M. Mørup, M. N. Schmidt, and L. K. Hansen, "Shift invariant sparse coding of image and music data," Neural Netw., 2008, submitted for publication.
54. K. Kreutz-Delgado, J. F. Murray, B. D. Rao, K. Engan, T.-W. Lee, and T. J. Sejnowski, "Dictionary learning algorithms for sparse representation," Neural Comput., vol.15, no.2, pp. 349-396, 2003.
55. M. Aharon, M. Elad, and A. M. Bruckstein, "The K-SVD: An algorithm for designing of overcomplete dictionaries for sparse representations," IEEE Trans. Signal Process., vol.54, no.11, pp. 4311-4322, Nov. 2006.