Modular recurrent neural networks for Mandarin syllable recognition

IEEE Transactions on Neural Networks

Volumn 9, Issue 6, 1998, Pages 1430-1441

  Chen, Sin Horng ^a,b   Liao, Yuan Fu ^b  

^a IEEE   (Taiwan)

^b NATIONAL CHIAO TUNG UNIVERSITY   (Taiwan)

Author keywords

Mandarin speech recognition; MCE GPD algorithms; Modular recurrent neural networks

Indexed keywords

ALGORITHMS; MARKOV PROCESSES; MATHEMATICAL MODELS; MAXIMUM LIKELIHOOD ESTIMATION; PROBABILITY; SPEECH RECOGNITION;

MANDARIN SYLLABLE RECOGNITION; MODULAR RECURRENT NEURAL NETWORKS;

RECURRENT NEURAL NETWORKS;

EID: 0032208401     PISSN: 10459227     EISSN: None     Source Type: Journal    
DOI: 10.1109/72.728393     Document Type: Article

References (49)

1. L. R. Rabiner, "A tutorial on hidden Markov models and selected applications in speech recognition," Proc. IEEE, vol. 77, no. 2, pp. 257-286, 1989.
2. Y. Normandin, "Maximum mutual information estimation of hidden Markov models," Automatic Speech And Speaker Recognition - Advanced Topics. Boston, MA: Kluwer, 1996, pp. 57-82.
3. C. H. Lee and J. L. Gauvain, "Bayesian adaptive learning and MAP estimation of HMM," Automatic Speech And Speaker Recognition - Advanced Topics. Boston, MA: Kluwer, 1996, pp. 83-108.
4. S. Katagiri, C. H. Lee, and B. H. Juang, "New discriminative training algorithms based on the generalized probabilistic descent method," in Proc. IEEE Neural Networks for Signal Process. (NNSP), 1991, pp. 299-308.
5. B. H. Juang, W. Chou and C. H. Lee, "Statistical and discriminative methods for speech recognition," Automatic Speech And Speaker Recognition - Advanced Topics. Boston, MA: Kluwer, 1996, pp. 109-132.
6. L. Niles, H. Sliverman, G. Tajchman, and M. Bush, "How limited training data can allow a neural network to outperform an 'optimal' statistical classifier," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing (ICASSP), 1989, pp. 17-20.
7. H. Bourland, and C. J. Wellekens, "Links between Markov models and multilayer perceptrons," IEEE Trans. Pattern Anal. Machine Intell., vol. 12, no. 12, pp. 1167-1178, 1990.
8. H. Bourlard and N. Morgan, Connectionist speech recognition - A hybrid approach. Boston, MA: Kluwer, 1994.
9. A. J. Robinson, "An application of recurrent nets to phone probability estimation," IEEE Trans. Neural Networks, vol. 5, pp. 298-305, Mar. 1994.
10. D. Kershaw, T. Robinson, and S. Renals, "The 1995 ABBOT LVCSR system for multiple unknown microphones," in Int. Conf. Spoken Language Processing (ICSLP), 1996.
11. R. A. Jacobs, M. I. Jordan, and A. G. Barto, "Task decomposition through competition in a modular connectionist architecture: The what and where vision tasks," Cognitive Sci., vol. 15, pp. 219-250, 1991.
12. B. L. M. Happel and Jacob M. J. Murre, "Design and evolution of modular neural-network architectures," Neural Networks, vol. 7, nos. 6/7, pp. 985-1004, 1994.
13. R. E. Jenkins and B. P. Yuhas, "A simplified neural-network solution through problem decomposition: The case of the truck backer-upper," IEEE Trans. Neural Networks, vol. 4, pp. 718-720, July 1993.
14. M. I. Jordan and R. A. Jacobs, "Hierarchical mixtures of experts and the EM algorithm," Neural Comput., vol. 6, pp. 181-214, 1994.
15. Y. Zhao, R. Schwartz, J. Sroka, and J. Makhoul, "Hierarchical mixtures of experts methodology applied to continuous speech recognition, in Advances in Neural Inform. Processing Syst. 7 (NIPS'7), 1995, pp. 859-865.
16. D. Kershaw, T. Robinson, and M. Hochberg, "Context-dependent classes in a hybrid recurrent network-HMM speech recognition system," in Advances in Neural Inform. Processing Syst. 8 (NIPS'8), 1996, pp. 750-756.
17. J. Fritsch, M. Finke, and A. Waibel, "Context-dependent hybrid HME/HMM speech recognition using polyphone clustering decision trees," in Proc. IEEE Int. Conf Acoust., Speech, Signal Processing (ICASSP), vol. 3, 1997, pp. 1759-1762.
18. A. Waibel, H. Sawai, and K. Shikano, "Modularity and scaling in large phonemic neural networks," IEEE Trans. Acoust., Speech, Signal Processing, vol. 37, pp. 1888-1898, Dec. 1989.
19. J. B. Hampshire II and A. Waibel, "The Meta-Pi network: Building distributed knowledge representations for robust multisource pattern recognition," IEEE Trans. Pattern Anal. Machine Intell., vol. 14, pp. 751-769, 1992.
20. I. C. Jou, M. S. Hu, and Y. T. Juang, "Mandarin syllables recognition based on one class one net neural network with modified selective update algorithm," in Wkshp. Notes 1992 IEEE Int. Wkshp. Intell. Signal Processing Commun. Syst., 1992, pp. 577-591.
21. _, "A neural-network-based speech recognition system for isolated Cantonese syllables," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing (ICASSP), vol. 4, pp. 3269-3272, 1997.
22. J. F. Wang, C. H. Wu, S. H. Chang, and J. Y. Lee, "A hierarchical neural-network model based on a C/V segmentation algorithm for isolated Mandarin speech recognition," IEEE Trans. Signal Processing, vol. 39, pp. 2141-2145, Sept. 1992.
23. L. S. Lee, C. Y. Tseng, H. Y. Gu, F. H. Liu, C. H. Chang, Y. H. Lin, and Y. Lee, etc., "Golden Mandarin (I) - A real-time Mandarin speech dictation machine for Chinese language with very large vocabulary," IEEE Trans. Speech Audio Processing, vol. 1, pp. 158-179, 1993.
24. P. C. Chang and B. H. Juang, "Discriminative training of dynamic programming based speech recognizers," IEEE Trans. Speech Audio Processing, vol. 1, pp. 135-143, 1993.
25. P. C. Chang, S. H. Chen, and B. H. Juang, "Discriminative analysis of distortion sequences in speech recognition," IEEE Trans. Speech Audio Processing, vol. 1, pp. 326-333, 1993.
26. L. S. Lee, C. Y. Tseng, K. J. Chen, I. J. Hung, M. Y. Lee, and L. F. Chien, etc., "Golden Mandarin (II) - An improved single-chip real-time Mandarin dictation machine for Chinese language with very large vocabulary," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing (ICASSP), vol. II, 1993, pp. 503-506.
27. R. Y. Lyu et al., "Golden Mandarin (III) - A user-adaptive prosodic-segment-based Mandarin dictation machine for Chinese language with very large vocabulary," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing (ICASSP), vol. I, 1995, pp. 57-60.
28. H. M. Wang, J. L. Shen, Y. J. Yang, C. Y. Tseng, and L. S Lee, "Complete recognition of continuous Mandarin speech for Chinese language with very large vocabulary but limited training data," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), vol. I, pp. 61-64, 1995.
29. J. K. Chen and F. K. Soong, "An N-best candidates-based discriminative training for speech recognition application," IEEE Trans. Speech Audio Processing, vol. 2, pt. II, pp. 206-216, Jan. 1994.
30. C. H. Lee and B. H. Juang, "A survey on automatic speech recognition with an illustrative example on continuous speech recognition of Mandarin," Computat. Linguistics Chinese Language Processing, vol. 1, no. 1, pp. 01-36, Aug. 1996.
31. W. Y. Chen, Y. F. Liao, and S. H. Chen, "Speech recognition with hierarchical recurrent neural networks," Pattern Recognition, vol. 28, no. 6, pp. 795-805, 1995.
32. C. C. Huand and J. F. Wang et al., "A Mandarin speech dictation system based on neural network and language processing model," IEEE Trans. Consumer Electron., vol. 40, no. 3, Aug. 1994.
33. P. C. Chang, S. W. Sue, and S. H. Chen, "Mandarin tone recognition by multilayer perceptron," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing (ICASSP), 1990, pp. 517-520.
34. Y. R. Wang, J. M. Shieh, and S. H. Chen, "Tone recognition of continuous Mandarin speech based on hidden Markov model," Int. J. Pattern Recog. Artific. Intell., vol. 8, pp. 233-246, 1994.
35. Y. R. Wang and S. H. Chen, "Tone recognition of continuous Mandarin speech assisted with prosodic information," J, Accoust. Soc. Amer., vol. 96, no. 5, pt. 1, pp. 2637-2645, Nov. 1994.
36. _, "Tone recognition of continuous Mandarin speech based on neural network," IEEE Trans. Speech Audio Processing, vol. 3, pp. 146-150, Mar. 1995.
37. B. Ma, T. Huang, B. Xu, X. Zhang, and F. Qu, "Context-dependent acoustic models for Chinese speech recognition," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing (ICASSP), vol. 1, pp. 455-458, 1996.
38. J. L. Elman, "Finding structure in time," Cognitive Sci., vol. 14, pp. 179-211, 1990.
39. T. W. Cacciatore and S. J. Nowlan, "Mixtures of controllers for jump linear and nonlinear plants," in Advances in Neural Inform. Processing Syst. 6 (NIPS'6), 1994, pp. 719-726.
40. Y. Bengio and P. Frasconi, "An input output HMM architecture," in Advances in Neural Inform. Processing Syst. 7 (NIPS'7), 1995, pp. 427-434.
41. A. Kehagial and V. Petridis, "Predictive modular neural networks for time series classification," Neural Networks, vol. 10, no. 1, pp. 31-49, 1997.
42. S. J. Lee, K. C. Kim, H. Yoon, and J. W. Cho, "Application of fully recurrent neural networks for speech recognition," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing (ICASSP), 1991, pp. 77-80.
43. M. M. Hochberg, G. D. Cook, S. J. Renals, and A. J. Robinson, "Connectionist model combination for large vocabulary speech recognition," In Proc. of ICSLP-94, 1994, pp. 1499-1502.
44. J. D. Markel and A. H. Gray, Jr., Linear prediction of speech. Berlin, Germany: Springer-Verlag, 1976.
45. H. C. Wang and H. F. Pai, "Recognition of Mandarin syllables based on the distribution of two-dimensional cepstral coefficients, Int. J. Pattern Recognition and Artificial Intell., vol. 8, no. 1, pp. 247-257, 1993.
46. Y. F. Liao, W. Y. Chen, and S. H. Chen, "Continuous Mandarin speech recognition using hierarchical recurrent neural network," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing (ICASSP), vol. 6, 1996, pp. 3371-3374.
47. S. H. Chen, Y. F. Liao, S. M. Chiang, and S. Chang, "An RNN-based preclassification method for fast continuous Mandarin speech recognition," IEEE Trans. Speech Audio Processing, vol. 6, pp. 86-90, Jan. 1998.
48. Y. F. Liao and S. H. Chen, "An MRNN-based method for continuous Mandarin speech recognition," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing (ICASSP), vol. 2, pp. 1121-1124, 1998.
49. T. Komori and S. Katagiri, "GPD training of dynamic programming-based speech recognizers," J. Acoust. Soc. Jpn. (E), vol. 13, no. 6, pp. 341-349, 1992.