Applying dynamic context into MLP/HMM speech recognition system

Computer Speech and Language

Volumn 15, Issue 3, 2001, Pages 233-255

  Salmela, Petri ^a  

^a TAMPERE UNIVERSITY OF TECHNOLOGY   (Finland)

Author keywords

[No Author keywords available]

Indexed keywords

MARKOV PROCESSES; MATHEMATICAL MODELS; MAXIMUM LIKELIHOOD ESTIMATION; SIGNAL TO NOISE RATIO; VECTORS;

FEATURE VECTORS; HIDDEN MARKOV MODELS; LINEAR DISCRIMINANT ANALYSIS;

SPEECH RECOGNITION;

EID: 0035412937     PISSN: 08852308     EISSN: None     Source Type: Journal    
DOI: 10.1006/csla.2001.0167     Document Type: Article

References (42)

1. Bishop, C. (1996). Neural Networks for Pattern Recognition. Oxford University Press, New York, USA.
2. Bourlard, H. & Wellekens, C. (1990). Links between Markov models and multilayer perceptrons. IEEE Transactions on Pattern Analysis and Machine Intelligence, 12, 1167-1178.
3. Bourlard, H. & Morgan, N. (1993). Continuous speech recognition by connectionist statistical methods. IEEE Transactions on Neural Networks, 4, 893-909.
4. Bourlard, H., D'hoore, B. & Boite, J. (1994). Optimizing recognition and rejection performance in wordspotting systems. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Adelaide, Australia, volume 1, pp. 373-376.
5. Chou, W. (2000). Discriminant-function-based minimum recognition error rate pattern-recognition approach to speech recognition. Proceedings of the IEEE, 88, 1201-1223.
6. Cook, G. & Robinson, T. (1998). Transcribing broadcast news with the 1997 Abbot system. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Seattle, USA, volume 2, pp. 917-920.
7. Deller, J., Proakis, G. & Hansen, J. (1993). Discrete-Time Processing of Speech Signals. Macmillan Publishing Company, New York, USA.
8. Deng, L., Askmanovic, M., Sun, X. & Wu, C. (1994). Speech recognition using hidden Markov models with polynomial regression function as nonstationary states. IEEE Transactions on Speech and Audio Processing, 2, 507-520.
9. Dugast, C., Devillers, L. & Aubert, X. (1994). Combining TDNN and HMM in a hybrid system for improved continuous-speech recognition. IEEE Transactions on Speech and Audio Processing, 2, 217-223.
10. Franco, H., Weintraub, M. & Cohen, M. (1997). Context modeling in a hybrid HMM-neural net speech recognition system. Proceedings of the IEEE International Conference on Neural Networks, Houston, Texas, USA, pp. 2089-2092.
11. Furui, S. (1986). Speaker independent isolated word recognition using dynamic features of speech spectrum. IEEE Transactions on Acoustics, Speech and Signal Processing, ASSP-34, 52-59.
12. Gu, H., Tseng, C. & Lee, L. (1991). Isolated-utterance speech recognition using hidden Markov models with bounded state durations. IEEE Transactions on Signal Processing, 39, 1743-1752.
13. Haeb-Umbach, R., Geller, D. & Ney, H. (1993). Improvements in connected digit recognition using linear discriminant analysis and mixture densities. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Minneapolis, MN, USA, pp. 239-242.
14. Huang, Z. & Kuh, A. (1992). A combined self-organizing feature map and multilayer perceptron for isolated word recognition. IEEE Transactions on Signal Processing, 40, 2651-2657.
15. Iso-Sipilä, J., Laurila, K. & Haavisto, P. (1996). Optimal adaptive garbage modelling in speech recognition. Proceedings of IEEE Nordic Signal Processing Symposium, Espoo, Finland, pp. 107-110.
16. Jelinek, F. (1998). Statistical Methods for Speech Recognition. The MIT Press, Massachusetts, USA.
17. Johnson, R. & Wichern, D. (1992). Applied Multivariate Statistical Analysis. Prentice Hall, New Jersey, USA.
18. Juang, B.-H., Chou, W. & Lee, C.-H. (1997). Minimum error rate methods for speech recognition. IEEE Transactions on Speech and Audio Processing, 5, 257-265.
19. Kangas, J. (1990). Time-delayed self-organizing maps. Proceedings of the International Joint Conference on Neural Networks, San Diego, California, USA, pp. 331-336.
20. Kangas, J. (1991). Time-dependent self-organizing maps for speech recognition. Proceedings of the 1991 International Conference on Artificial Neural Networks, Espoo, Finland, pp. 1591-1594.
21. Katagiri, S., Lee, C.-H. & Juang, B.-H. (1991). New discriminative training algorithms based on the generalized probabilistic descent method. Proceedings of the 1991 IEEE Workshop on Neural Networks for Signal Processing, Princeton, New Jersey, USA, pp. 299-308.
22. Kepuska, V. & Gowdy, J. (1989). Investigation of phonemic context in speech using self-organizing feature maps. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Glasgow, Scotland, pp. 504-507.
23. Kohonen, T. (2001). Self-Organizing Maps. 3rd edition. Springer-Verlag, New York, USA.
24. Kokkonen, M. & Torkkola, K. (1990). Using self-organizing maps and multi-layered feed-forward nets to obtain phonemic transcription of spoken utterances. Speech Communication, 9, 541-549.
25. Krogh, A. & Riis, S. (1999). Hidden neural networks. Neural Computation, 11, 541-563.
26. Laurila, K. (1997). Noise robust speech recognition with state duration constraints. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Munich, Germany, pp. 871-874.
27. Morgan, N. & Bourland, H. (1995). Neural networks for statistical recognition of continuous speech. Proceedings of the IEEE, 83, 741-770.
28. Morgan, N., Ellis, D., Fosler-Lussier, E., Janin, A. & Kingsbury, B. (1999). Reducing errors by increasing the error rate: MLP acoustic modelling for broadcast news transcription. Proceedings of the DARPA Broadcast News Workshop, Herndon, Virginia.
29. Nguyen, D. & Widrow, B. (1990). Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptive weights. Proceedings of International Joint Conference of Neural Networks, San Diego, California, USA, pp. 21-26.
30. Ostendorf, M. (1996). From HMMs to segment models: stochastic modelling for CSR. In Automatic Speech and Speaker Recognition (C.-H. Lee, F. Soong and K. Paliwal, eds), pp. 185-210. Kluwer Academic Publishers, Norwell, MA, USA.
31. Petek, B., Waibel, A. & Tebelskis, J. (1991). Integrated phoneme-function word architecture of hidden control neural networks for continuous speech recognition. Proceedings of the European Conference on Speech Communication and Technology, Genova, Italy, pp. 1407-1410.
32. Rabiner, L. Tutorial on hidden Markov models and selected applications in speech recognition. Proceedings of the IEEE, 77, 257-286.
33. Richard, M. & Lippmann, R. (1991). Neural network classifiers estimate Bayesian a posteriori probabilities. Neural Computation, 3, 461-483.
34. Robinson, T., Hochberg, M. & Renals, S. (1994). IPA: improved phone modelling with recurrent neural networks. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Adelaide, Australia, pp. 37-40.
35. Robinson, T., Hochberg, M. & Renals, S. (1996). The use of recurrent neural networks in continuous speech recognition. In Automatic Speech and Speaker Recognition (C.-H. Lee, F. Soong and K. Paliwal, eds), pp. 233-258. Kluwer Academic Publishers, Norwell, MA, USA.
36. Salmela, P., Laurila, K., Lehtkangas, M. & Saarinen, J. (1999a). On string level training in MLP/HMM speech recognition system. Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics, Tokyo, Japan, pp. 165-171.
37. Salmela, P., Lehtokangas, M. & Saarinen, J. (1999b). Neural network based digit recognition system for voice dialling in noisy environments. International Journal of Information Sciences, 121, 171-199.
38. Senior, A. & Robinson, T. (1996). Forward-backward retraining of recurrent neural networks. In Advances in Neural Information Processing Systems 8 (D. Touretzky, M. Mozer and M. Hasselmo, eds), pp. 743-749. The MIT Press, Massachusetts, USA
39. Tebelskis, J. (1995). Speech recognition using neural networks. PhD dissertation, School of Computer Science, Carnegie Mellon University, CMU-CS-95-142, Pittsburgh, Pennsylvania, USA.
40. Viikki, O. & Laurila, K. (1998). Cepstral domain segmental feature vector normalization for noise robust speech recognition. Speech Communication, 25, 133-147.
41. Vogl, T., Mangis, J., Rigler, A., Zink, W. & Alkon, D. (1988). Accelerating the convergence of the back-propagation method. Biological Cybernetics, 59, 257-263.
42. Young, S., Russell, N. & Thornton, J. (1989). Token Passing: A Simple Conceptual Model for Connected Speech Recognition Systems. Technical Report, University of Cambridge, Department of Engineering, Cambridge, England.