Noise-robust automatic speech recognition using a predictive echo state network

IEEE Transactions on Audio, Speech and Language Processing

Volumn 15, Issue 5, 2007, Pages 1724-1730

  Skowronski, Mark D ^a,b   Harris, John G ^a  

^a UNIVERSITY OF FLORIDA   (United States)

^b UNIVERSITY OF WESTERN ONTARIO   (Canada)

Author keywords

Digit recognition; Noise robust automatic speech recognition; Predictive echo state network

Indexed keywords

HIDDEN MARKOV MODELS; RECURRENT NEURAL NETWORKS; SIGNAL TO NOISE RATIO;

AUTOMATIC SPEECH RECOGNITION; COMPUTATIONAL COSTS; CONVENTIONAL METHODS; DIGIT RECOGNITION; ECHO STATE NETWORKS; HIGH-DIMENSIONAL; NOISE-ROBUST AUTOMATIC SPEECH RECOGNITION; TIME SERIES PREDICTION;

SPEECH RECOGNITION;

EID: 34548827187     PISSN: 15587916     EISSN: None     Source Type: Journal    
DOI: 10.1109/TASL.2007.896669     Document Type: Article

References (43)

1. E. Levin, "Word recognition using hidden control neural architecture," in Proc. Int. Conf. Acoust., Speech, Signal Process., Albuquerque, NM, Apr. 1990, vol. 1, pp. 433-436.
2. K. Iso and T. Watanabe, "Large vocabulary speech recognition using neural prediction model," in Proc. Int. Conf. Acoust., Speech, Signal Process., Toronto, ON, Canada, May 1991, vol. 1, pp. 57-60.
3. J. Tebelskis and A. Waibel, "Large vocabulary recognition using linked predictive neural networks," in Proc. Int. Conf. Acoust., Speech, and Signal Process., Albuquerque, NM, Apr. 1990, vol. 1, pp. 437-440.
4. J. Tebelskis, "Speech recognition using neural networks," Ph.D. dissertation, Carnegie Mellon Univerity, Pittsburgh, PA, 1995.
5. B. Petek, "On the predictive connectionist models for automatic speech recognition," in Proc. Int. Conf. Acoust., Speech, Signal Process., Istanbul, Turkey, Jun. 2000, vol. 1, pp. 3442-3445.
6. C. M. Bishop, Neural Networks for Pattern Recognition. New York: Oxford Univ. Press, 1995.
7. N. Morgan and H. A. Bourlard, "Neural networks for statistical recognition of continuous speech," Proc. IEEE, vol. 83, no. 5, pp. 742-772, May 1995.
8. H. Gish, "A probabilistic approach to the understanding and training of neural network classifiers," in Proc. Int. Conf. Acoust., Speech, Signal Process., Albuquerque, NM, Apr. 1990, vol. 1, pp. 1361-1364.
9. A. J. Robinson, "An application of recurrent nets to phone probability estimation," IEEE Trans. Neural Netw., vol. 5, no. 2, pp. 298-305, Mar. 1994.
10. M. Franzini, K.-F. Lee, and A.Waibel, "Connectionist Viterbi training: A new hybrid method for continuous speech recognition," in Proc. Int. Conf. Acoust., Speech, Signal Process., Albuquerque, NM, Apr. 1990, vol. 1, pp. 425-428.
11. A. Graves and J. Schmidhuber, "Framewise phoneme classification with bidirectional LSTM and other neural network architectures," Neural Netw., vol. 18, no. 5-6, pp. 602-610, Jun.-Jul. 2005.
12. E. Trentin and M. Gori, "Robust combination of neural networks and hidden Markov models for speech recognition," Neural Netw., vol. 14, no. 6, pp. 1519-1531, Nov. 2003.
13. C. Neukirchen, J. Rottland, D. Willett, and G. Rigoll, "A continuous density interpretation of discrete hmm systems and mmi-neural networks," IEEE Trans. Speech Audio Process., vol. 9, no. 4, pp. 367-377, May 2001.
14. L. R. Rabiner, "A tutorial on hidden Markov models and selected applications in speech recognition," in Readings in Speech Recognition, A. Waibel and K.-F Lee, Eds. San Mateo, CA: Kaufmann, 1990, pp. 267-296.
15. J. R. Deller, J. H. L. Hansen, and J. G. Proakis, Discrete-Time Processing of Speech Signals. New York: Macmillan, 1993.
16. H. G. Hirsch and D. Pearce, "The Aurora experimental framework for the performance evaluation of speech recognition systems under noise conditions," in Proc. Int. Speech Commun. Assoc. Tutorial Res. Workshop ASR2000, Paris, France, 2000, pp. 181-188.
17. D. E. Rumelhart, G. E. Hinton, and R. J. Williams, "Learning internal representations by error propagation," in Parallel Distributed Processing: Explorations in the Microstructure of Cognition, D. E. Rumelhart and J. L. McClelland, Eds. Cambridge, MA: MIT Press, 1986, vol. 1, Foundations, pp. 318-362.
18. S. Haykin, Neural Networks: A Comprehensive Foundation, 2nd ed. Upper Saddle River, NJ: Prentice-Hall, 1999.
19. J. L. Elman and D. Zipser, "Learning the hidden structure of speech," J. Acoust. Soc. Amer., vol. 83, no. 4, pp. 1615-1626, Apr. 1988.
20. A. F. Atiya and A. G. Parlos, "New results on recurrent network training: Unifying the algorithms and accelerating convergence," IEEE Trans. Neural Netw., vol. 11, no. 3, pp. 697-709, May 2000.
21. H. Jaeger, "The "echo state" approach to analysing and training recurrent neural networks," German National Res. Center Inf. Technol., Fraunhofer Inst. Auton. Intell. Syst., GMD Rep. 148, Dec. 2001, Tech. Rep.
22. S. Haykin, Adaptive Filter Theory, 4th ed. Upper Saddle River, NJ: Prentice-Hall, 2001.
23. H. Jaeger, "Adaptive nonlinear system identification with echo state networks," in Advances in Neural Information Processing Systems, 2002, S. T. S. Becker and K. Obermayer, Eds. Cambridge, MA:MIT Press, 2003, pp. 593-600.
24. H. Jaeger and H. Haas, "Harnessing nonlinearity: Predicting chaotic systems and saving energy in wireless communication," Science, vol. 304, no. 5667, pp. 78-80, 2004.
25. M. D. Skowronski and J. G. Harris, "Automatic speech recognition using a predictive echo state network classifier," Neural Netw., 2007, to be published.
26. R. O. Duda, P. E. Hart, and D. G. Stork, Pattern Classification, 2nd ed. New York: Wiley, 2001.
27. S. Haykin, "Signal processing in a nonlinear, non-Gaussian and nonstationary world," in Nonlinear Speech Modeling and Applications, G. Chollet, A. Esposito, M. Faundez-Zanuy, and M. Marinaro, Eds. Berlin: Springer-Verlag, 2005, pp. 43-53.
28. B.-H. Juang and L. R. Rabiner, "The segmental K-means algorithm for estimating parameters of hidden Markov models," IEEE Trans. Acoust., Speech, Signal Process., vol. 38, no. 9, pp. 1639-1641, Sep. 1990.
29. R. A. Jacobs, M. I. Jordan, S. J. Nowlan, and G. E. Hinton, "Adaptive mixtures of local experts," Neural Comput., vol. 3, no. 1, pp. 79-87, Spring, 1991.
30. S. Young, J. Jansen, J. Odell, D. Ollasen, and P. Woodland, The HTK Book (Version 2.0). Cambridge, U.K.: Entropics Cambridge Research Lab, 1995.
31. M. D. Skowronski and J. G. Harris, "Exploiting independent filter bandwidth of human factor cepstral coefficients in automatic speech recognition," J. Acoust. Soc. Amer., vol. 116, no. 3, pp. 1774-1780, Sep. 2004.
32. S. Furui, "Cepstral analysis technique for automatic speaker verification," IEEE Trans. Acoust., Speech, Signal Process., vol. ASSP-29, no. 2, pp. 254-272, Apr. 1981.
33. B. S. Atal, "Effectiveness of linear prediction characteristics of the speech wave for automatic speaker identification and verification," J. Acoust. Soc. Amer., vol. 55, no. 6, pp. 1304-1312, Jun. 1974.
34. K. Murphy, Hidden Markov Model Toolbox for Matlab, Jun. 7, 2006[Online]. Available: http://www.cs.ubc.ca/̃murphyk/Software/HMM/ hmm.html
35. H. Jaeger, "Reservoir riddles: Suggestions for echo state network research," in Proc. Int. Joint Conf. Neural Netw.,Montreal, QC, Canada, Jul. 2005, pp. 1460-1462.
36. D. Prokhorov, "Echo state networks: Appeal and challenges," in Proc. Int. Joint Conf. Neural Netw., Montreal, QC, Canada, Jul. 2005, pp. 1463-1466.
37. T. M. Cover, "Geometrical and statistical properties of systems of linear inequalities with applications in pattern recognition," IEEE Trans. Electron. Comput., vol. EC-14, no. 3, pp. 326-334, Jun. 1965.
38. H. Jaeger, A tutorial on training recurrent neural networks, covering BPPT, RTRL, EKF and the "echo state network" approach German National Res. Center Inf. Technol., Fraunhofer Inst. Auton. Intell. Syst., Oct. 2002, Tech. Rep.
39. Y. Ephraim and H. L. Van Trees, "A signal subspace approach for speech enhancement," IEEE Trans. Speech Audio Process., vol. 3, no. 4, pp. 251-266, Jul. 1995.
40. B. Strope and A. Alwan, "A model of dynamic auditory perception and its application to robust word recognition," IEEE Trans. Speech Audio Process., vol. 5, no. 5, pp. 451-464, Sep. 1997.
41. Y. Gong, "Speech recognition in noisy environments: A survey," Speech Commun., vol. 16, pp. 261-291, 1995.
42. L. Deng, J. Droppo, and A. Acero, "Dynamic compensation of hmm variances using the feature enhancement uncertainty computed from a parametric model of speech distortion," IEEE Trans. Speech Audio Process., vol. 13, no. 3, pp. 412-421, May 2005.
43. M. D. Skowronski and J. G. Harris, "Noise-robust automatic speech recognition using a discriminative echo state network," in Proc. Int. Symp. Circuits Syst., New Orleans, LA, 2007, to be published.