ASR systems in noisy environment: Analysis and solutions for increasing noise robustness

Radioengineering

Volumn 20, Issue 1, 2011, Pages 74-84

  Rajnoha, Josef ^a   Pollák, Petr ^a  

^a CZECH TECHNICAL UNIVERSITY IN PRAGUE   (Czech Republic)

Author keywords

Feature extraction; Front end; Noisy speech; Parameterization; Robust ASR; Robust speech recognition; Spectral subtraction; Voice activity detection

Indexed keywords

EID: 79955978656     PISSN: 12102512     EISSN: None     Source Type: Journal    
DOI: None     Document Type: Article

References (36)

1. OPENSHAW, J. P., MASON, J. S. On the limitations of Cepstral features in noise. In Proc. ICASSP, 1994, vol. 2, p. 49-52.
2. WET, F. de, CRANEN, B., VETH, J. de, BOVES, L. A comparison of LPC and FFT-based acoustic features for noise robust ASR. In Eurospeech 2001, p. 865-868.
3. CHOI, E. Noise robust front-end for ASR using spectral subtraction, spectral flooring and cumulative distribution mapping. In Proc. 10th Australian Int. Conf. on Speech Science and Technology, SST'04. Sydney (Australia), Dec. 2004, p. 451-456.
4. GALES, M. J. F., YOUNG, S. J. Parallel Model Combination for Speech Recognition in Noise. Technical report CUED/FINFENG/ TR 135, Cambridge, England, 1993.
5. HERMANSKY, H., SHARMA, S. Temporal patterns (TRAPs) in ASR of noisy speech. In ICASSP '99: Proc. of IEEE Int. Conf. on the Acoustics, Speech, and Signal Processing. Washington DC (USA), IEEE Computer Society, 1999, p. 289-292.
6. DAVIS, S., MERMELSTEIN, P. Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Transactions on Acoustics, Speech and Signal Processing, Aug 1980, vol. 28, p. 357-366.
7. HERMANSKY, H. Perceptual linear predictive (PLP) analysis of speech. In Proc. JASA, April 1990, vol. 87, no. 4.
8. KANG, G. S., FRANSEN, L. J. Quality improvement of LPCprocessed noisy speech by using spectral subtraction. IEEE Trans. on ASSP, June 1989, vol. 37, no. 6, p. 939-942.
9. BABA ALI, B., SAMETI, H., SAFAYANI, M. Likelihoodmaximizing-based multi-band spectral subtraction for robust speech recognition. EURASIP Journal on Advances in Signal Processing, 2009. Article ID 878105, 15 p.
10. XU, C., LIU, Y., YANG, Y. S., et al. A system for Mandarin short phrase recognition on portable devices. In Proc. of Int. Symp. on Chinese Spoken Language Processing, 2004.
11. EPHRAIM, Y., MALAH, D. Speech enhancement using a minimum mean square error short time spectral amplitude estimator. IEEE Trans. on ASSP, Dec. 1984, vol. 32, no. 6, p. 1109-1121.
12. MING, J., JANCOVIC, P., HANNA, P., STEWART, D. Modeling the mixtures of known noise and unknown unexpected noise for robust speech recognition. In Proc. of Eurospeech'2001. Aalborg (Denmark), 2001, p. 579-582.
13. VARGA, A. P., MOORE, R. E. Hidden Markov model decomposition of speech and noise. In Proc. ICASSP, 1990, p. 845-848.
14. LIAO, Y. F., FANG, H. H., HSU, C. H. Eigen-MLLR environment/ speaker compensation for robust speech recognition. In Proc. Interspeech'08. Brisbane (Australia), September 2008, p. 1249-1252.
15. LEGGETTER, C. J., WOODLAND, P. C. Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models. Computer Speech & Language, April 1995, vol. 9, no. 2, p. 171-185.
16. GAUVAIN, J. L., LEE, C. H. Maximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chains. IEEE Trans. on SAP, 1994, vol. 2, no. 2, p. 291-298.
17. FISHER, A., STAHL, V. Database and online adaptation for improved speech recognition in car environments. In Proc. ICASSP'99, p. 445-448.
18. HERMANSKY, H. TRAP-TANDEM: Data-driven extraction of temporal features from speech. In Proc. of ASRU'03. Martigny (Switzerland), 2003, p. 255-260.
19. UMESH, S., COHEN, L., NELSON, D. Fitting the Mel scale. In Proc. ICASSP, 1999, vol. 1, p. 217-220.
20. HÖNIG, F., STEMMER, G., HACKER, C., BRUGNARA, F. Revising Perceptual Linear Prediction (PLP). In Eurospeech 2005, p. 2997-3000.
21. ZOLNAY, A., SCHLÜTER, R., NEY, H. Acoustic feature combination for robust speech recognition. In ICASSP'05. Philadelphia (PA, USA), March 2005, vol. 1, p. 457-460.
22. SCHLÜTER, R., BEZRUKOV, I., WAGNER, H., NEY, H. Gamma tone features and feature combination for large vocabulary speech recognition. In ICASSP 2007. Honolulu (HI, USA), April 2007, p. 649-652.
23. LI, Q., SOONG, F. K., SIOHAN, O. An auditory system-based feature for robust speech recognition. In Eurospeech 2001, p. 619-622.
24. PSUTKA, J., MÜLLER, L., PSUTKA, J. V. The influence of a filter shape in the telephone-based recognition module using PLP parameterization. In TSD 2001. Berlin, Springer-Verlag 2001, p. 222-228.
25. PSUTKA, J., MÜLLER, L., PSUTKA, J. V. Comparison of MFCC and PLP parameterizations in the speaker independent continuous speech recognition task. In Eurospeech 2001, p. 1813-1816.
26. FOUSEK, P., POLLÁK, P. Additive noise and channel distortionrobust parameterization tool - performance evaluation on Aurora 2&3. In Eurospeech 2003, p. 1785-1788.
27. nd Int. Conf. on Informatics Research for Development of Knowledge Society Infrastructure. ICKS. IEEE Computer Society, Washington, DC, 2007, p. 69-76.
28. MARTIN, R. Noise power spectral density estimation based on optimal smoothing and minimum statistics. IEEE Tran. on Speech and Audio Processing, July 2001, vol. 9, no. 5, p. 504 - 512.
29. SOVKA, P., POLLÁK, P., KYBIC, J. Extended spectral subtraction. In European Signal Processing Conference (EUSIPCO'96). Trieste (Italy), September 1996.
30. NOVOTNY, J., MACHACEK, L. Noise reduction applied in real time speech recognition system. In Polish-Czech-Hungarian Workshop on Circuit Theory, Signal Processing, and Telecommunication Networks. Budapest (Hungary), September 2001.
31. HTK speech recognition toolkit. [Online]. Ver. 3.3. July 2005. Available at: http://htk.eng.cam.ac.uk/
32. CtuCopy. [Online]. Ver. 3.0.11. Available at: http://noel.feld.cvut.cz/speechlab/en/download/CtuCopy_3.0.11.tar.bz2
33. SPEECON database distributed through the European Language Resources Association [Online]. Available at: http://catalog.elra.info/search_result.php?keywords=speecon&language=en&osCsid=66
34. HIRSCH, H. G., PEARCE, D. The AURORA experimental framework for the performance evaluations of speech recognition systems under noisy conditions. In ISCA ITRW ASR2000 Automatic Speech Recognition: Challenges for the Next Millennium. Paris (France), September 2000.
35. RAJNOHA, J., POLLÁK, P. Voice activity detection based on perceptual cepstral analysis. In Technical Computing Prague 2008 [CD-ROM]. Prague: HUMUSOFT, 2008, vol. 1, p. 1-9. (in Czech).
36. ETSI Distributed speech recognition ES 202 050 standard [online]. Available at: http://www.etsi.org/WebSite/Technologies/DistributedSpeechRecognition.aspx