Cantonese syllable recognition using neural networks

IEEE Transactions on Speech and Audio Processing

Volumn 7, Issue 4, 1999, Pages 466-472

  Lee, Tan ^a   Ching, P C ^a  

^a CHINESE UNIVERSITY OF HONG KONG   (Hong Kong)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; COMPUTATIONAL LINGUISTICS; MULTILAYER NEURAL NETWORKS; PATTERN RECOGNITION SYSTEMS; RECURRENT NEURAL NETWORKS;

BASE SYLLABLE RECOGNIZER; CANTONESE SYLLABLE RECOGNITION; TONE RECOGNIZER;

SPEECH RECOGNITION;

EID: 0032677483     PISSN: 10636676     EISSN: None     Source Type: Journal    
DOI: 10.1109/89.771317     Document Type: Article

References (26)

1. L. R. Rabiner and B. H. Juang, Fundamentals of Speech Recognition. Englewood Cliffs, NJ: Prentice-Hall, 1993.
2. H. Bourlard and N. Morgan, Connectionist Speech Recognition-A Hybrid Approach. Boston, MA: Kluwer, 1994.
3. J. Barnett étal., "Comparative performance in large vocabulary isolated word recognition in five European languages," in Proc. 4th Eur. Conf. Speech Communication and Technology, vol. 1, pp. 189-192.
4. S. Ann, "Current status and prospects of speech processing technology in Korea," in Proc. 1994 Int. Symp. Speech, Image Processing, and Neural Nehvorks, vol. 1, pp. 133-136.
5. T.-H. Ho et al., "Fast and accurate continuous speech recognition for Chinese language with very large vocabulary," in Proc. 4th Eur. Conf. Speech Communication and Technology, vol. 1, pp. 211-214.
6. P. C. Ching, T. Lee, and E. Zee, "From phonology and acoustic properties to automatic recognition of Cantonese," in Proc. 1994 Int. Symp. Speech, Image Processing and Neural Nerivorks, vol. 1, pp. 127-132.
7. H.-M. Wang et al., "Complete recognition of continuous Mandarin speech for Chinese language with very large vocabulary but limited training data," in Proc. 1995 Int. Conf. Acoustics, Speech and Signal Processing, vol. 1, pp. 61-64.
8. L. Zhou and S. Imai, "Chinese all syllables recognition using combination of multiple classifiers," in Proc. 1996 Int. Conf. Acoustics, Speech and Signal Processing, vol. 6, pp. 3494-3497.
9. S. Potisuk, M. P. Harper, and J. T. Gandour, "Speaker-independent automatic classification of Thai tones in connected speech by analysissynthesis method," in Proc. 1995 Int. Conf. Acoustics, Speech, Signal Processing, vol. 1, pp. 632-635.
10. T. Lee, P. C. Ching, and L. W. Chan, "Recurrent neural network for speech modeling and speech recognition," in Proc. 1995 Int. Conf. Acoustics, Speech, and Signal Processing, vol. 5, pp. 3319-3322.
11. T. Lee, P. C. Ching, and L. W. Chan, "An RNN based speech recognition system with discriminative training," in Proc. 1995 Europ. Conf. Speech Communication and Technology, Madrid, Spain, vol. 3, pp. 1667-1670.
12. T. Lee, "Automatic recognition of isolated cantonese syllables using neural networks," Ph.D. dissertation, Chinese Univ. Hong Kong, May 1996.
13. Linguistic Society of Hong Kong, Newsletter, no. 15, pp. 32-39.
14. Y.-R. Chao, A Grammar of Spoken Chinese, trans. T. P. Hsin. Hong Kong: Chinese Univ. Press, 1980.
15. T. Lee et al., 'Tone recognition of isolated Cantonese syllables," IEEE Trans. Speech Audio Processing, vol. 3, pp. 204-209, 1995.
16. M. M. Sondhi, "New methods of pitch extraction," IEEE Trans. Audio Electroacoust., vol. AU-16, pp. 262-266, June 1968.
17. T. Lee and P. C. Ching, "A neural network based speech recognition system for isolated Cantonese syllables," in Proc. 1997 Int. Conf. Acoustics, Speech and Signal Processing, vol. 4, pp. 3269-3272.
18. L. W. Chan and F. Y. Young, "Using recurrent network for time series prediction," in Proc. 1993 World Congr. Neural Nehvorks, vol. 4, pp. 332-336.
19. Z. Zeng, R. M. Goodman, and P. Smyth, "Discrete recurrent neural networks for grammatical interference," IEEE Trans. Neural Networks, vol. 5, pp. 320-30, 1994.
20. L. Jin, P. N. Nikiforuk, and M. M. Gupta, "Approximation of discretetime state-space trajectories using dynamic recurrent neural networks," IEEE Trans. Automat. Contr., vol. 40, pp. 1266-1270, 1995.
21. A. J. Robinson, "An application of recurrent nets to phone probability estimation," IEEE Trans. Neural Networks, vol. 5, pp. 298-305, Mar. 1994.
22. W.-Y. Chen, Y.-F. Liao, and S.-H. Chen, "Speech recognition with hierarchical recurrent neural networks," Pattern Recognit., vol. 28, pp. 795-805.
23. R. J. Williams and D. Zipser, "A learning algorithm for continually running fully recurrent neural networks," Neural Comput., vol. 1, pp. 270-280.
24. T. Lee and P. C. Ching, "On improving discrimination capability of an RNN based recognizer," in Proc. 1996 Int. Conf. Spoken Language Processing, Philadelphia, PA, vol. 1, pp. 526-529.
25. 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, Apr. 1993.
26. T. Lee, P. C. Ching, and L. W. Chan, "Isolated word recognition using modular recurrent neural networks," Pattern Recognit., vol. 31, pp. 751-760, 1998.