Additive background noise as a source of non-linear mismatch in the cepstral and log-energy domain

Computer Speech and Language

Volumn 19, Issue 1, 2005, Pages 31-54

  De Wet, Febe ^a   De Veth, Johan ^a   Boves, Loe ^a   Cranen, Bert ^a  

^a RADBOUD UNIVERSITY NIJMEGEN   (Netherlands)

Author keywords

[No Author keywords available]

Indexed keywords

DATA REDUCTION; IMAGE PROCESSING; MATHEMATICAL MODELS; NOISE ABATEMENT; RESEARCH; SIGNAL PROCESSING; SPEECH TRANSMISSION; STATISTICAL METHODS;

BACKGROUND NOISE; CHANNEL DISTORTION; MISMATCH REDUCTION TECHNIQUES; SPEECH SIGNALS;

SPEECH RECOGNITION;

EID: 9644259306     PISSN: 08852308     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.csl.2003.12.003     Document Type: Article

References (38)

1. Adami, A., Burget, L., Dupont, S., Garudadri, H., Grezl, F., Hermansky, H., Jain, P., Kajarekar, S., Morgan, N., Sivadas, S., 2002. QUALCOMM-ICSI-OGI features for ASR. In: Proceedings of ICSLP 2002, pp. 21-24, Denver, CO, USA.
2. Atal, B., 1974. Effectiveness of linear prediction characteristics of the speech wave for automatic speaker identification and verification. Journal of the Acoustical Society of America 55, 1304-1312.
3. Basseville, M., 1989. Distance measures for signal processing and pattern recognition. Signal Processing 18, 349-369.
4. Claes, T., van Compernolle, D., 1996. Spectral estimation and normalisation for robust speech recognition. In: Proceedings of ICSLP 1996, pp. 1997-2000, Philadelphia, PA, USA.
5. Cook, G.D., Christie, J.D., Clarkson, P.R., Hochberg, M.M., Logan, B.T., 1996. Real-time recognition of broadcast radio speech. In: Proceedings of ICASSP 1996, vol. I, pp. 141-144, Atlanta, GA, USA.
6. de la Torre, A., Segura, J.C., Benitez, M.C., Peinado, A.M., Rubio, A.J., 2002. Non-linear transformation of the feature space for robust speech recognition. In: Proceedings of ICASSP 2002, Orlando, FL, USA.
7. de Veth, J., Boves, L., 2003. On the efficiency of classical RASTA filtering for continuous speech recognition: keeping the balance between acoustic pre-processing and acoustic modelling. Speech Communication 39, 269-286.
8. de Veth, J., de Wet, F., Cranen, B., Boves, L., 2001 a. Acoustic features and a distance measure that reduce the impact of training-test mismatch in ASR. Speech Communication 34 (1-2), 57-74.
9. de Veth, J., Mauuary, L., Noé, B., de Wet, F., Sienel, J., Boves, L., Jouvet, D., 2001b. Feature vector selection to improve ASR robustness in noisy conditions. In: Proceedings of Eurospeech 2001, pp. 201-204, Aalborg, Denmark.
10. de Wet, F., de Veth, J., Cranen, B., Boves, L., 2002. Accumulated Kullback divergence for the analysis of ASR performance in the presence of noise. In: Proceedings of ICSLP 2002, pp. 1069-1073, Denver, CO, USA.
11. Dharanipragada, S., Padmanabhan, M., 2000. A nonlinear unsupervised adaptation technique for speech recognition. In: Proceedings of ICSLP 2000, vol. IV, pp. 556-559, Beijing, China.
12. ETSI, 2002. Speech processing, transmission and quality aspects (STQ); distributed speech recognition; advanced front-end feature extraction algorithm; compression algorithms. Available from 〈http://pda.etsi.org/pda/queryform. asp〉 (search on 'aurora').
13. Furui, S., 1981. Cepstral analysis technique for automatic speaker verification. IEEE Transactions on Acoustics, Speech and Signal Processing ASSP-29, 254-272.
14. Hermansky, H., Morgan, N., 1991. Compensation for the effect of the communication channel in auditory-like analysis of speech (RASTA-PLP). In: Proceedings of Eurospeech 1991, pp. 1367-1370, Genova, Italy.
15. Hermansky, H., Morgan, N., 1994. RASTA processing of speech. IEEE Transactions on Speech and Audio Processing 2, 578-589.
16. Hilger, F., Ney, H., 2001. Quantile based histogram equalisation. In: Proceedings of Eurospeech 2001, pp. 1135-1138, Aalborg, Denmark.
17. Hirsch, H.-G., Ehrlicher, C., 1995. Noise estimation techniques for robust speech recognition. In: Proceedings of ICASSP 1995, pp. 153-146, Michigan, USA.
18. Hirsch, H.-G., Meyer, P., Ruehl, H., 1991. Improved speech recognition using high-pass filtering of subband envelopes. In: Proceedings of Eurospeech 1991, pp. 413-416, Genova, Italy.
19. Hirsch, H.-G., Pearce, D., 2000. The Aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions. In: Proceedings of ASR 2000, pp. 181-188, Paris, France.
20. ITU, 1996. ITU recommendation G.712: "Transmission performance characteristics of pulse code modulation channels". Available from 〈http://www.itu.int/〉.
21. Junqua, J.-C., Haton, J.-P., 1996. On the use of a robust speech representation. In: Robustness in Automatic Speech Recognition: Fundamentals and Applications. Kluwer Academic Publishers, Boston, USA.
22. Kessens, J.M., Wester, M., Strik, H., 1999. Improving the performance of a Dutch CSR by modeling within-word and cross-word pronunciation variation. Special issue of Speech Communication: Modeling Pronunciation Variation for Automatic Speech Recognition 29 (2-4), 193-207.
23. Kullback, S., 1959. Information Theory and Statistics. Wiley, New York.
24. Lockwood, P., Boudy, J., 1992. Experiments with a nonlinear spectral subtracter (NNS) hidden Markov models and the projection, for robust speech recognition in cars. Speech Communication 11, 215-228.
25. Macho, D., Mauuary, L., Noé, B., Cheng, Y.-M., Ealey, D., Jouvet, D., Kelleher, H., Pearce, D., Saadoun, F., 2002. Evaluation of noise-robust DSR front-end on Aurora databases. In: Proceedings of ICSLP 2002, pp. 17-20, Denver, CO, USA.
26. Mokbel, C., Pachès-Leal, P., Jouvet, D., Monné, J., 1994. Compensation of telephone line effects for robust speech recognition. In: Proceedings of ICSLP 1994, pp. 987-990, Yokohama, Japan.
27. Molau, S., Pitz, M., Ney, H., 2001. Histogram normalisation in the acoustic feature space. In: Proceedings of ASRU 2001, Madonna di Campiglio, Trento, Italy.
28. NIST, 1999. NIST SNR evaluation software. Available from 〈http://www.itl.nist.gov/iaui/894.01/〉.
29. Noé, B., Sienel, J., Jouvet, D., Mauuary, L., Boves, L., de Veth, J., de Wet, F., 2001. Noise reduction for noise robust feature extraction for distributed speech recognition, In: Proceedings of Eurospeech 2001, pp. 433-436, Aalborg, Denmark.
30. Openshaw, J.P., Mason, J.S., 1994. Optimal noise-masking of cepstral features for robust speaker identification. In: ESCA Workshop on automatic speaker recognition, identification and verification, pp. 231-234, Martigny, Switzerland.
31. Rosenberg, A., Lee, C.-H., Soong, F., 1994. Cepstral channel normalization techniques for HMM-based speaker verification. In: Proceedings of ICSLP 1994, pp. 1835-1838, Yokohama, Japan.
32. Rus, J.C., 1995. The Image Processing Handbook. CRC Press, Boca Raton, FL.
33. Segura, J.C., Benitez, C., de la Torre, A., Rubio, A., 2002. Feature extraction combining spectral noise reduction and cepstral histogram equalisation for robust ASR. In: Proceedings of ICSLP 2002, pp. 225-228, Denver, CO, USA.
34. Steinbiss, V., Ney, H., Aubert, X., Besling, S., Dugast, C., Essen, U., Geller, D., Haeb-Umbach, R., Kneser, R., Meier, H.-G., Oerder, M., Tran, B.-H., 1995. The Philips research system for continuous-speech recognition. Philips Journal of Research 49, 317-352.
35. Strik, H., Russel, A., van den Heuvel, H., Cucchiarini, C., Boves, L., 1997. A spoken dialogue system for the Dutch public transport information service. International Journal of Speech Technology 2, 119-129.
36. Tibrewala, S., Hermansky, H., 1997. Multi-band and adaptation approaches to robust speech recognition. In: Proceedings of Eurospeech 1997, pp. 2619-2622, Rhodes, Greece.
37. Viikki, A., Laurila, K., 1998. Cepstral domain segmental feature vector normalization for noise robust speech recognition. Speech Communication 25, 133-147.
38. Young, S., Jansen, J., Odell, J., Ollason, D., Woodland, P., 1997. The HTK Book (for HTK Version 2.1). Cambridge University Press, Cambridge.