Noise condition-dependent training based on noise classification and SNR estimation

IEEE Transactions on Audio, Speech and Language Processing

Volumn 15, Issue 8, 2007, Pages 2431-2443

  Xu, Haitian ^a   Dalsgaard, Paul ^b   Tan, Zheng Hua ^b   Lindberg, Børge ^b  

^a Toshiba Reseach Europe Ltd   (United Kingdom)

^b AALBORG UNIVERSITY   (Denmark)

Author keywords

Condition dependent training; Noise classification; Robust speech recognition; Robustness to unknown noise; Signal to noise ratio (SNR) estimation

Indexed keywords

CONDITION-DEPENDENT TRAINING; NOISE CLASSIFICATION; ROBUST SPEECH RECOGNITION; ROBUSTNESS TO UNKNOWN NOISE; SIGNAL-TO-NOISE RATIO (SNR) ESTIMATION;

ACOUSTIC INTENSITY; COMPUTATIONAL COMPLEXITY; ESTIMATION; HIDDEN MARKOV MODELS; MATERIALS HANDLING; METEORITES; REMELTING; SPEECH ANALYSIS; SPEECH RECOGNITION;

SIGNAL TO NOISE RATIO;

EID: 64349084660     PISSN: 15587916     EISSN: None     Source Type: Journal    
DOI: 10.1109/TASL.2007.906188     Document Type: Article

References (27)

1. S. Das, A. Nadas, D. Nahamoo, and M. Picheny, "Adaptation techniques for ambience and microphone system," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process., 1994, vol. 1, pp. 21-23.
2. R. P. Lippmann, E. A. Martin, and D. B. Paul, "Multi-style training for robust isolated-word speech recognition," in Proc. ICASSP'87, 1987, pp. 705-708.
3. Y. Gong, "Speech recognition in noisy environments: A survey," Speech Commun., vol. 16, pp. 261-291, 1995.
4. M. Akbacak and J. H. L. Hansen, "Environmental sniffing: Noise knowledge estimation for robust speech systems," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process., Apr. 6-10, 2003, vol. 2, pp. 113-116.
5. L. Ma, D. J. Smith, and B. P. Milner, "Context awareness using environmental noise classification," in Proc. Eurospeech'03, 2003, pp. 2237-2240.
6. M. Akbacak and J. H. L. Hansen, "Advances in acoustic noise tracking for robust in-vehicle speech systems," in Advances for In-Vehicle and Mobile Systems, H. Abut, J. H. L. Hansen, and K. Takeda, Eds. New York: Springer, 2007, ch. 10, pp. 109-122.
7. J. G. Fiscus, "A post-processing system to yield reduced word error rates: Recognizer output voting error reduction (ROVER)," in Proc. IEEE Workshop Autom. Speech Recognition Understanding, 1997, pp. 347-354.
8. T. Kitamura, S. Ando, and E. Hayahara, "Speaker-independent spoken digit recognition in noisy environments using dynamic spectral features and neural networks," in Proc. Int. Conf. Speech Lang. Process., 1992, vol. 1, pp. 699-702.
9. X. Cui and Y. Gong, "Modeling variance variation in a variable parameter HMM framework for noise robust speech recognition," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process., 2006, vol. 1, pp. 1117-1120.
10. Z. Zhang, T. Sugimura, and S. Furui, "A tree-structured clustering method integrating noise and SNR for piecewise linear-transformation- based noise adaptation," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process., 2004, vol. 1, pp. 981-984.
11. Z. Zheng, T. Ohya, and S. Furui, "Evaluation of tree-structured piecewise- linear-transformation-based noise adaptation on Aurora 2 database," in Proc. Int. Conf. Spoken Lang. Process., Jeju, Korea, 2004, vol. 1, pp. 113-116.
12. H. Xu, Z.-H. Tan, P. Dalsgaard, and B. Lindberg, "Robust speech recognition based on noise and SNR classification-A multiple-model framework," in Proc. Interspeech 2005, Lisbon, Portugal, Sep. 2005, pp. 977-980.
13. H. Xu, Z.-H. Tan, P. Dalsgaard, and B. Lindberg, "Robust speech recognition from noise-type based feature compensation and model interpolation in a multiple model framework," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process., Toulouse, France, May 2006, pp. I-1141-I-1144.
14. O. Viikki and K. Laurila, "Cepstral domain segmental feature vector normalization for noise robust speech recognition," Speech Commun., vol. 25, pp. 133-147, 1998.
15. Speech Processing, Transmission and Quality Aspects (STQ); Distributed Speech Recognition; Advanced Front-End Feature Extraction Algorithm; Compression Algorithms, ETSI standard doc, 2006.
16. S. Sagayama, Y.Yamaguchi, and S. Takahashi, "Jacobian adaptation of noisy speech models," in Proc. IEEE Workshop Autom. Speech Recognition Understanding, Dec. 1997, pp. 396-403.
17. X. D. Huang, M.-Y. Hwang, J. Li, and M. Mahajan, "Deleted interpolation and density sharing for continuous hidden Markov models," in Proc. Int. Conf. Acoust., Speech, Signal Process., 1996, pp. 885-888.
18. P. Moreno, "Speech recognition in noisy environments," Ph.D. dissertation, Carnegie Mellon Univ., Pittsburgh, PA, 1996.
19. H. G. Hirsch and D. Pearce, "The Aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions," in Proc. ISCA ITRW ASR2000 (Autom. Speech Recognition: Challenges for the Next Millennium), Paris, France, Sep. 18-20, 2000, pp. 18-20.
20. S. Young, "HTK: Hidden Markov Model Toolkit V1.5," Eng. Dept. Speech Group and Entropic Research Lab. Inc., Cambridge Univ., Washington, DC, 1993.
21. L. Lamel, L. Rabiner, A. Rosenberg, and J. Wilpon, "An improved endpoint detector for isolated word recognition," IEEE Trans. Acoust., Speech, Signal Process., vol. ASSP-29, no. 4, pp. 777-785, Aug. 1981.
22. J. Barker, L. Josifovski, M. Cooke, and P. Green, "Soft decisions in missing data techniques for robust automatic speech recognition," in Proc. ICSLP'00, Beijing, China, 2000, vol. 1, pp. 373-376.
23. M. Cooke, P. Green, L. Josifovski, and A. Vizinho, "Robust automatic speech recognition with missing and unreliable acoustic data," Speech Commun., vol. 34, no. 3, pp. 267-285, Jun. 2001.
24. R. Martin, "Noise power spectral density estimation based on optimal smoothing and minimum statistics," IEEE Trans. Speech Audio Process., vol. 9, no. 4, pp. 504-512, Jul. 2001.
25. E. W. Weisstein, "Hypothesis Testing," MathWorld, 2005 [Online]. Available: http://mathworld.wolfram.com/HypothesisTesting.html
26. P. Heeman and D. Cole, SpeechDatCar: US English. Beaverton, OR: Oregon Graduate Inst., 2001.
27. D. Marcho et al., "Evaluation of a noise-robust DSR front-end on Aurora databases," in Proc. ICSLP'02, Denver, CO, 2002, pp. 17-20.