HMM-based Speech Recognition using DMS Model and Fuzzy Concept

DMS 모델과 퍼지 개념을 이용한 HMM에 기초를 둔 음성 인식

  • 안태옥 (호원대학교 컴퓨터게임학부)
  • Published : 2008.08.31


This paper proposes a HMM-based recognition method using DMSVQ(Dynamic Multi-Section Vector Quantization) codebook by DMS(Dynamic Multi-Section) model and fuzzy concept, as a study for speaker- independent speech recognition. In this proposed recognition method, training data are divided into several dynamic section and multi-observation sequences which are given proper probabilities by fuzzy rule according to order of short distance from DMSVQ codebook per each section are obtained. Thereafter, the HMM using this multi-observation sequences is generated, and in case of recognition, a word that has the most highest probability is selected as a recognized word. Other experiments to compare with the results of recognition experiments using proposed method are implemented as a data by the various conventional recognition methods under the equivalent environment. Through the experiment results, it is proved that the proposed method in this study is superior to the conventional recognition methods.


DMS;DMSVQ;fuzzy concept;multi-observation


  1. Hiroaki Sakoe and Seibi Chiba, "Dynamic Programming Algorithm Optimization for Spoken Word Recognition",IEEE Trans. on Acoustics, Speech and Signal Processing, Vol. ASSP-26, No. 1, pp. 43-49, Feb. 1978.
  2. R. M. Gray, " Vector Quantization", IEEE ASSP Magazine, Vol. 1, pp. 4-29, Apr. 1984
  3. D. K. Burton, J. E. Shore and J. T. Buck, " Isolated-Word Speech Recognition using Multisection Vector Quantization Codebooks", IEEE Trans. of Acoustics, Speech, Signal Processing, Vol. ASSP-33, No. 4, Aug. 1985.
  4. Tae Ock Ann and Sun hyub Kim, "An automatic Speech Recognition of Computer Using Time Sequential Vector Quantization", The Institute of Electronics Engineers of Korea, Vol. 27, No. 7, July. 1990.
  5. Tae Ock Ann and Young Kyu Byun, "A Study on Speech Recognition using DMS Model", The Acoustical Society of Korea, Vol. 13, No. 2E, pp. 41-50, Dec. 1994.
  6. L. R. Rabiner and B. H. Juang, " An Intorduction to Hidden Markov Models", IEEE ASSP Magazine, JAN. 1986.
  7. T. O. Ann, Y. G. Byun and S. H. Kim, "Korean Speech Recognition using DHMM", The Acoustical Society of Korea, Vol. 10. No. 1, pp. 52-61, Feb. 1991.
  8. 안태옥, 변용규, 김순협, “MSVQ를 이용한 HMM에 의한 단독어 인식”, 대한전자 공학회, 제 27권 제 9호, pp. 158-165, Sep. 1990.
  9. 안태옥, “Speech Recognition using MSHMM based on Fuzzy Concept", 한국 음향학회지, 제16권 2E호, pp. 55-61, Sep. 1997.