This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
A Mandarin Dictation Machine Based Upon a Hierarchical Recognition Approach and Chinese Natural Language Analysis
July 1990 (vol. 12 no. 7)
pp. 695-704

An experimental Mandarin dictation machine for inputting Mandarin speech (spoken Chinese language) into computers is described. Because of the special characteristics of the Chinese language, syllables are chosen as the basic units for dictation. The machine is designed based on a hierarchical language recognition approach in which acoustic signals are first recognized as a sequence of syllables, possible word hypotheses are then formed from the syllables, and the complete sentences are finally obtained. This approach is implemented by two subsystems. The first recognizes the syllables using speech signal processing techniques, the second subsystem then identifies the exact characters from the syllable and corrects the errors in syllable recognition. The detailed syllable recognition algorithms, word formation rules, parser, grammar, and the syntactic checking algorithms are described. With newspaper text in the form of isolated syllables as input, the preliminary test results indicate that such a dictation machine is not only practically attractive, but technically feasible.

[1] Proc. 1986 and 1987 Int. Conf. Chinese Computing, Chinese Lang. Comput. Soc., Singapore, Aug. 1986, Chicago, IL, June 1987.
[2] A. Averbuchet al., "An IBM PC based large-vocabulary isolatedword recognizer," inProc. 1986 Int. Conf. Acoustics, Speech, Signal Processing, vol. 1, Tokyo, Japan, Apr. 1986, pp. 53-56.
[3] M. Pichenyet al., "A real-time IBM PC based large-vocabulary isolated-word speech recognizer," Pinner, England, Voice Processing, Online Publ., 1986.
[4] A. M. Derouault, "Context-dependent Markov models for large-vocabulary speech recognition," inProc. 1987 Int. Conf. Acoustics, Speech, Signal Processing, Dallas, TX, Apr. 1987.
[5] B. Merialdo, "Speech recognition with very large size dictionary," inProc. 1987 Int. Conf. Acoustics, Speech, Signal Processing, Dallas, TX, Apr. 1987, pp. 364-367.
[6] L.-S. Lee, C.-Y. Tseng, K. J. Chen, and J. Huang, "The preliminary results for a Mandarin dictation machine based upon Chinese natural language analysis," inProc. 1987 Int. Joint Conf. Artificial Intelligence, Milano. Italy, Aug. 1987.
[7] Y. R. Chao.A Grammar of Spoken Chinese. Berkeley, CA: University of California Press, 1968.
[8] S.-M. Lei and L.-S. Lee, "Digital synthesis of Mandarin speech using its special characteristic,"J.-Chinese Inst. Eng., vol. 61 no. 2, pp. 107-115, Mar. 1983.
[9] V. A. Fromkin,Tone--A Linguistic Survey. New York: Academic, 1978.
[10] H.-y. Gu, C.-y. Tseng, and L.-s. Lee, "A comparative study on the performance of several speech recognition techniques applied on the highly confusing Mandarin syllables,"J. Chines; Inst. Eng., 1989.
[11] M.-S. Yu. G.-S. Chen. C.-C. Hsiao. C.-Y. Tseng. and L.-S. Lee. "A preliminary approach to complete vocabulary Mandarin syllable recognition," inProc. 1986 Int. Conf. Chinese Computing, Singapore, Aug. 1986, pp. 168-171.
[12] C.-W. Hwang, C.-Y. Tseng, and L.-S. Lee. "An efficient Mandarin vowel recognition system based upon multi-section vector quentization and branch-and-bound classification techniques," inProc. 1986 Int. Computer Symp., Tainan, Taiwan, Rep. of China, Dec. 1986.
[13] D. K. Burton, J. E. Shore, and I. T. Buck, "Isolated-word speech recognition using multi-section vector quantization codebooks,"IEEE Trans. Acoust., Speech, Signal Processing, vol. ASSP-33, no. 4, Aug. 1985.
[14] C.-H. Wu, C.-Y. Tseng, and L.-S. Lee, "New speech recognition approaches for the Mandarin consonants based upon hidden Markov models, " inProc. 1987 Nat. Computer Symp., Taipei, Taiwan, Rep. of China, Dec. 1987, pp. 971-979.
[15] P.-Y. Ting, C.-Y. Tseng, and L.-S. Lee, "New speech recognition approaches based upon finite state vector quantization with structural constraints," inProc. 1988 Int. Conf. Acoustics, Speech, Signal Processing, New York, Apr. 1988.
[16] J.-C. Lee, "Mandarin lexical tone recognition based on vector quantization and hidden Macov models," Master's thesis, Tsing-Hua Univ., Taiwan, Rep. of China, May 1986.
[17] C.-G. Chen, K.-J. Chen, and L.-S. Lee, "A model for lexical analysis and parsing of Chinese sentences," inProc. 1986 Int. Conf. Chinese Computing, Singapore, Aug. 1986, pp. 33-40.
[18] C. Li and S. Thompson,Mandarin Chinese: A Functional Reference Grammar. Berkeley, CA: University of California Press, 1981.
[19] J. Huang, "Logical relations in Chinese and the theory of grammar," Ph.D. dissertation, Massachusetts Inst. Technol., 1982.
[20] L.-J. Lin, K.-J. Chen, J. Huang, and L.-S. Lee, "SASC: A syntactic analysis system for Chinese sentences," inProc. 1986 Int. Conf. Chinese Computing, Singapore, Aug. 1986. pp. 29-32.
[21] L.-J. Lin, J. Huang. K.-J. Chen. and L.-S. Lee, "A Chinese natural language processing system based upon the theory of empty categories." inProc. Fifth Nat. Conf. Artijcial Intelligence, AAAI, Philadelphia, PA, Aug. 1986, pp. 1059-1062.

Index Terms:
speech recognition; Mandarin dictation machine; Chinese; natural language analysis; syllables; hierarchical language recognition; acoustic signals; speech signal processing; word formation rules; parser; grammar; syntactic checking algorithms; natural languages; speech recognition; voice equipment
Citation:
L.s. Lee, C.y. Tseng, K.J. Chen, J. Huang, C.h. Hwang, P.Y. Ting, L.j. Lin, C.C. Chen, "A Mandarin Dictation Machine Based Upon a Hierarchical Recognition Approach and Chinese Natural Language Analysis," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 12, no. 7, pp. 695-704, July 1990, doi:10.1109/34.56213
Usage of this product signifies your acceptance of the Terms of Use.