은닉 마코프 모델 기반 병렬음성인식 시스템

A Parallel Speech Recognition System based on Hidden Markov Model

  • 정상화 (부산대학교 컴퓨터공학과) ;
  • 박민욱 (부산대학교 컴퓨터공학과)
  • Jeong, Sang-Hwa (Dept.of Computer Science Engineering, Busan National University) ;
  • Park, Min-Uk (Dept.of Computer Science Engineering, Busan National University)
  • 발행 : 2000.12.01

초록

본 논문의 병렬음성인식 모델은 연속 은닉 마코프 모델(HMM; hidden Markov model)에 기반한 병렬 음소인식모듈과 계층구조의 지식베이스에 기반한 병렬 문장인식모듈로 구성된다. 병렬 음소인식 모듈은 수천개의 HMM을 병렬 프로세서에 분산시킨 수, 할당된 HMM에 대한 출력확률 계산과 Viterbi 알고리즘을 담당한다. 지식베이스 기반 병렬 문장인식모듈은 음소모듈에서 공급되는 음소열과 지안하는 병렬 음성인식 알고리즘은 분산메모리 MIMD 구조의 다중 트랜스퓨터와 Parsytec CC 상에 구현되었다. 실험결과, 병렬 음소인식모듈을 통한 실행시간 향상과 병렬 문장인식모듈을 통한 인식률 향상을 얻을 수 있었으며 병렬 음성인식 시스템의 실시간 구현 가능성을 확인하였다.

키워드

참고문헌

  1. P. Baggia, E. Gerbino, et al, 'Efficient representation of linguistic knowledge in continuous speech understanding,' Proceedings of IJCAI 91, 1991
  2. S.-H. Chung, D.I Moldovan, and R.F. DeMara, A Parallel Computational Model for Integrated Speech and Natural Language Understanding, IEEE Transactions on Computers, vol. 42, no. 10, pp. 1171-1183, 1993 https://doi.org/10.1109/12.257704
  3. S. Davis, P. Mermelstein, 'Comparison of parametric representation for monosyllabic word recognition in continuously spoken sentences,' in IEEE Trans. ASSP, pp 357-266, 1980
  4. E.P. Giachin and C.Rullent, A Parallel Parser for Spoken Natural Language, Proceedings of IJCAI, pp. 1537-1542, 1989
  5. X. Huang and L. Guthrie, 'Parsing in Parallel,' Proceedings of COLING-86, pp, 140-145, 1986 https://doi.org/10.3115/991365.991403
  6. G. Huijsen, Parallel Implementation of Hidden Markov Models on the nCUBE2, M.Sc. thesis, Alparon report, nr. 96-03, Delft University of Technology, 1996
  7. M.Y. Hwand and X.D Huang, Shared-Distribution Hidden Markov Models for Speech Recognition, IEEE Trans. on SAP, vol.1, no.4 pp.414-420, 1993 https://doi.org/10.1109/89.242487
  8. K.F. Lee, H.W. Hon, Speaker-Independent Phone Recognition Using Hidden Markov Models, in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing, Vol. 37, No 11, Nov. pp. 1641-1648, 1989 https://doi.org/10.1109/29.46546
  9. K.F.Lee,Context-dependent phonetic hidden Markov models for speaker-independent continuous speech recognition, IEEE Trans. Acoust., Speech, Signal Processing, vol. 38, no. 4, Apr. pp. 599-609, 1990 https://doi.org/10.1109/29.52701
  10. K.F.Lee, F. Alleva, Continuous Speech Recognition, in Advances in Speech Signal Processing, pp. 623-650, 1992
  11. Y.J. Lee, Design and Construction of Korean Speech Database, Final report, ETRI, 1996
  12. L. Rabiner and B. H. Juang, Fundamentals of Speech Recognition, Prentice-Hall, New Jersey, 1993
  13. R. M. Schwartz, Y. L. Chow, S.Roucos, M. Krasner, and J. Makhoul, Improved hidden Markov modeling of phoneme for continuous speech recognition, in IEEE Int. Conf. Acoustics, Speech, and Signal Processing, 1984
  14. F.J. Smith, J. Ming, P. O'Boyle, A.D. Irvine, A Hidden Markov Model with Optimized Inter-Frame Dependence, Proc. of ICASSP, pp. 209-212, 1995 https://doi.org/10.1109/ICASSP.1995.479401
  15. Steven Phillips, Anne Rogers, Parallel Speech Recognition, In Preceedings of EUROSPEECH-97, pp.135-138, 1997
  16. D. L. Waltz and J. B. Pollack, 'Massively Parallel Parsing: A Strong Interactive Model of Natural Language Interpretation,' Cognitive Science 9, pp. 51-74, 1985
  17. http://www.parsytec.de/top/products/cc-pp.htm
  18. 박민욱,정상화,김형순,'HMM기반 음소인식의 병렬 구현', 병렬처리시스템 학술발표회 논문집, 제9권,제 1호,pp.117-125,1998