Techniques for handling convolutional distortion with 'missing data' automatic speech recognition

Speech Communication

Volumn 43, Issue 1-2, 2004, Pages 123-142

  Palomäki, Kalle J ^a,b,c   Brown, Guy J ^b   Barker, Jon P ^b  

^a AALTO UNIVERSITY   (Finland)

^b UNIVERSITY OF SHEFFIELD   (United Kingdom)

^c UNIVERSITY OF HELSINKI   (Finland)

Author keywords

Missing data; Reverberation; Spectral distortion; Spectral normalisation; Speech recognition

Indexed keywords

AUTOMATION; CONVOLUTION; DATA REDUCTION; MARKOV PROCESSES; MATHEMATICAL MODELS; REVERBERATION; SPEECH ANALYSIS; SPEECH COMMUNICATION;

MISSING DATA; SPECTRAL DISTORTIONS; SPECTRAL NORMALIZATION; SPEECH SPECTRUM;

SPEECH RECOGNITION;

EID: 2942539074     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.specom.2004.02.005     Document Type: Article

References (59)

1. Akbacak M., Hansen J.H.L. Environmental sniffing: noise knowledge estimation for robust speech systems. Proc. ICASSP-2003. II:2003;113-116.
2. Avendano, C., 1997. Temporal processing of speech in a time-feature space, PhD thesis, Oregon graduate institute.
3. Assmann P., Summerfield Q. The perception of speech under adverse acoustic conditions. Greenberg S., Ainsworth W. Speech Processing in the Auditory System (Springer Handbook of Auditory Research, Vol. 18). 2003;Springer-Verlag.
4. Atal B.S. Effectiveness of linear prediction characteristics of the speech wave for automatic speaker identification and verification. J. Acoust. Soc. Am. 55:1974;1304-1312.
5. Barker J., Cooke M.P., Ellis D.P.W. Decoding speech in the presence of other sound sources. Proc. ICSLP-2000. IV:2000;270-273.
6. Barker J., Josifovski L., Cooke M.P., Green P.D. Soft decisions in missing data techniques for robust automatic speech recognition. Proc. ICSLP-2000. I:2000;373-376.
7. Barker J., Cooke M.P., Green P.D. Robust ASR based on clean speech models: An evaluation of missing data techniques for connected digit recognition in noise. Proc. Eurospeech-2001. 2001;213-217.
8. Barker, J., Green, P.D., Cooke, M.P., 2001b. Linking auditory scene analysis and robust ASR by missing data techniques, In: Proceedings of the Workshop on Innovations in Speech Processing (WISP-2001), Stratford-upon-Avon, UK, 2nd-3rd April.
9. Bradley J.S. Predictors of speech intelligibility in rooms. J. Acoust. Soc. Am. 80:1986;837-845.
10. Bregman A.S. Auditory Scene Analysis. 1990;MIT Press, Cambridge, MA.
11. Brown G.J., Cooke M.P. Computational auditory scene analysis. Comp. Speech Lang. 8:1994;297-336.
12. Brown G.J., Barker J., Wang D.L. A neural oscillator sound separator for missing data speech recognition. Proc. IJCNN-2001. 2001;2907-2912.
13. Cole R.A., Noel M., Lander T., Durham T. New telephone speech corpora at CSLU. Proc. Eurospeech-1995. I:1995;821-824.
14. Cooke M.P. Modelling Auditory Processing and Organization. 1993;Cambridge University Press, Cambridge, UK.
15. Cooke M.P., Green P.D., Josifovski L., Vizinho A. Robust automatic speech recognition with missing and unreliable acoustic data. Speech Comm. 34:2001;267-285.
16. Davis S.P., Mermelstein P. Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Trans. Acoust. Speech Signal Process. ASSP-28:1980;357-366.
17. Droppo J., Acero A., Deng L. Uncertainty decoding with SPLICE for noise robust speech recognition. Proc. ICASSP-2002. I:2002;57-60.
18. Drullman R., Festen J.M., Plomp R. Effects of temporal envelope smearing on speech reception. J. Acoust. Soc. Amer. 95:1994;1053-1064.
19. Dupont, S., Ris C., 1999. Assessing local noise level estimation methods. In: Proc. of Workshop on Robust Methods for Speech Recognition in Adverse Environments, pp. 115-118.
20. Eronen A., Tuomi J., Klapuri A., Fagerlund S., Sorsa T., Lorho G., Huopaniemi J. Audio context awareness - acoustic modeling and perceptual evaluation. Proc. ICASSP-2003. V:2003;529-532.
21. Gold B., Morgan N. Speech and Audio Signal Processing. 2000;John Wiley and Sons, Inc. New York.
22. Gölzer H., Kleinschmidt M. Importance of early and late reflections for automatic speech recognition in reverberant environments. Proc. Elektronische Sprachsignalverarbeitung (ESSV). 2003.
23. Hermansky H. Perceptual linear predictive (PLP) analysis of speech. J. Acoust. Soc. Am. 87:1990;1738-1752.
24. Hermansky H. Should recognisers have ears? Speech Comm. 25:1998;3-27.
25. Hermansky H., Morgan N. RASTA processing of speech. IEEE Trans. Speech Audio Proc. 2:1994;578-589.
26. Hermansky H., Ellis D.P.W., Sharma S. Tandem connectionist feature extraction for conventional HMM systems. Proc. ICASSP-2000. III:2000;1635-1638.
27. Hirsch H.G., Erlicher C. Noise estimation techniques for robust speech recognition. Proc. ICASSP-1995. I:1995;153-156.
28. Houtgast T., Steeneken H.J.M. A review of the MTF concept in room acoustics and its use for estimating speech intelligibility in auditoria. J. Acoust. Soc. Am. 77:1985;1069-1077.
29. Hyvärinen A., Karhunen J., Oja E. Independent Component Analysis. 2001;John Wiley and Sons, New York.
30. ISO 3382, 1997. Acoustics - Measurement of the Reverberation Time of Rooms with Reference to Other Acoustical Parameters, second ed. ISO, Geneva, Switzerland.
31. ITU-T recommendation G.712, 1996a. Transmission performance characteristics of pulse code modulated channels. International Telecommunications Union, Geneva.
32. ITU-T recommendation P.830, 1996b. Subjective performance assessment of telephone band and wide band digital codecs. International Telecommunications Union, Geneva.
33. Kandera N., Arai T., Hermansky H., Pavel M. On the relative importance of various components of the modulation spectrum for automatic speech recognition. Speech Comm. 28:1999;43-55.
34. Kingsbury, B.E.D., 1998. Perceptually inspired signal-processing strategies for robust speech recognition in reverberant environments. PhD thesis, University of California, Berkeley.
35. Kingsbury B.E.D., Morgan N., Greenberg S. Robust speech recognition using the modulation spectrogram. Speech Comm. 25:1998;117-132.
36. Kleinschmidt M., Hohmann V. Sub-band SNR estimation using auditory feature processing. Speech Comm. 39(1-2):2003;47-64.
37. Li D., Sethi I.K., Dimitrova N., McGee T. Classification of general audio data for content-based retrieval. Pattern Recognition Lett. 22:2001;533-544.
38. Lippmann R.P. Speech recognition by machines and humans. Speech Comm. 22:1997;1-15.
39. Luo Y., Du L. Single gauss model set-based data imputation method for complex ASR task. Proc. ISCAS 2003. II:2003;564-567.
40. Martin, K.D., 1999. Sound source recognition. PhD thesis, MIT, Massachusetts.
41. Martin R. An efficient algorithm to estimate the instantaneous SNR of speech signals. Proc. Eurospeech-1993. 1993;37-40.
42. Mathworks, Inc., 2003. MATLAB release 13 reference manual. Natick, MA.
43. Moore B.C.J. An Introduction to the Psychology of Hearing. fifth ed. 2003;Academic Press, Cambridge, UK.
44. Morris, A.C., 2002. Analysis of noise PDF transformation in secondary feature processing. IDIAP Research Report 02-29, IDIAP, Martigny, Switzerland.
45. Morris A.C., Cooke M.P., Green P.D. Some solutions to the missing feature problem in the classification, with application to noise-robust ASR. Proc. ICASSP-1998. II:1998;737-740.
46. Nabelek A.K., Robinson P.K. Monaural and binaural speech perception in reverberation for listeners of various ages. J. Acoust. Soc. Amer. 71:1982;1242-1248.
47. Omologo M., Svaizer P., Matassoni M. Environmental conditions and acoustic transduction in hands-free speech recognition. Speech Comm. 25:1998;75-95.
48. Oppenheim A.V., Schafer R.W. Discrete Time Signal Processing. 1989;Prentice Hall.
49. Palomäki, K.J., Brown, G.J., Wang, D.L., 2001. A binaural auditory model for missing data speech recognition in noisy and reverberant conditions. In: Proc. CRAC Eurospeech-2001 satellite workshop, Aalborg, 2nd September.
50. Palomäki K.J., Brown G.J., Barker J. Missing data speech recognition in reverberant conditions. Proc. ICASSP-2002. I:2002;65-68.
51. Palomäki, K.J., Brown, G.J., Wang, D.L., in press. A binaural processor for missing data speech recognition in the presence of noise and small-room reverberation. Speech Comm.
52. Patterson, R.D., Holdsworth, J.W., Nimmo-Smith, I., Rice, P., 1988. SVOS Final Report: The Auditory Fiterbank. APL Report 2341.
53. Pearce D., Hirsch H.-G. The aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions. Proc. ICSLP-2000. 4:2000;29-32.
54. Peltonen V., Tuomi J., Klapuri A., Huopaniemi J., Sorsa T. Computational auditory scene recognition. ICASSP-2002. II:2002;1941-1944.
55. Raj, B., 2000. Reconstruction of incomplete spectrograms for robust speech recognition. PhD thesis, Carnegie Mellon University, Pittsburgh, Pennsylvania.
56. Raj, B., Seltzer, M.L., Stern, R.M., in press. Reconstruction of Missing Features for Robust Speech Recognition, Speech Comm.
57. Rosenberg A.E., Lee C.-H., Soong F.K. Cepstral channel normalisation techniques for HMM-based speaker verification. Proc. ICSLP 94. 4:1994;1835-1838.
58. STRUT Version 2.4, 1997. Step by step guide to using the speech training and recognition unified tool STRUT. Available from 〈www.tcts.fpms.ac.be/ asr/project/strut/〉.
59. Young, S., Evermann, G., Kershaw, D., Moore, G., Odell, J., Ollason, D.,Valtchev, V., Woodland, P., 2001. The HTK Book, Revised for Version 3.1, Cambridge University Engineering Department, Available from 〈htk.eng.cam. ac.uk/〉.