The KIPS Transactions:PartB (정보처리학회논문지B)

Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

Phonetic Acoustic Knowledge and Divide And Conquer Based Segmentation Algorithm

음성학적 지식과 DAC 기반 분할 알고리즘

  • Koo, Chan-Mo (Dept.of Industry Engineering, Graduate School of Ajou University) ;
  • Wang, Gi-Nam (Dept.of Industry Engineering, Ajou University)
  • 구찬모 (아주대학교 대학원 산업공학과) ;
  • 왕지남 (아주대학교 산업공학과)
  • Published : 2002.04.01
Download PDF
⟨ Previous Next ⟩

Abstract

This paper presents a reliable fully automatic labeling system which fits well with languages having well-developed syllables such as in Korean. The ASL System utilize DAC (Divide and Conquer), a control mechanism, based segmentation algorithm to use phonetic and acoustic information with greater efficiency. The segmentation algorithm is to devide speech signals into speechlets which is localized speech signal pieces and to segment each speechlet for speech boundaries. While HMM method has uniform and definite efficiencies, the suggested method gives framework to steadily develope and improve specified acoustic knowledges as a component. Without using statistical method such as HMM, this new method use only phonetic-acoustic information. Therefore, this method has high speed performance, is consistent extending the specific acoustic knowledge component, and can be applied in efficient way. we show experiment result to verify suggested method at the end.

본 논문에서는 음절이 잘 발달되어 있는 한국어에 대해서 신뢰할 수 있는 완전 자동화된 레이블링 시스템을 제안한다. 음운 및 음향학적인 정보를 최대한 이용하고 분할에러를 줄이기 위해서 조절 메카니즘의 하나로 DAC개념을 사용하여 음성을 speechlet으로 나누고 분할 된 음성 구간에 대해서 레이블링을 시도하는 DAC기반 분할알고리즘이다. HMM방법이 획일적이고 확정적인 성능을 갖는 반면 본 제안 방법은 음성학적인 특화지식을 컴포넌트로 개발 추가 계속 향상시킬 수 있는 프레임워크를 제시하고 있다는 점에서 주요 의의가 있다고 하겠다. MM과 같은 통계학적인 방법을 이용하지 않고 음운학적, 음향학적 지식만을 이용하는 새로운 방법은 수행속도와 음성학적인 특화 지식컴포넌트를 확장함에 따라 일관성이 있으며 효과적 방법으로 적용가능 할 것이다. 제안 방법을 검증하기 위하여 실험결과를 제시하였다.

Keywords

References

  1. 엄태수, '한국어의 음운규칙 연구', pp.172-264, 1999
  2. 허웅, '국어음운학', 정음사, pp.129-280, 1984
  3. E. Vidal and A. Marzal, 'A review and new approaches for automatic segmentation of speech signals, Signal Processing V : Theories and Applications (L. Torres, E. Masgrau, and M. A. Lagunas, eds.),' Elsevier Science Publisher, Amsterdam, pp.43-53, 1990
  4. F. Brugnara, D. Falavigua, and M. Omologo, 'Automatic segmentation and labelling of speech based on hidden Markov models,' Speech Communication pp.357-370, 1993 https://doi.org/10.1016/0167-6393(93)90083-W
  5. J. P. Hosom, 'Automatic time alignment of phonemes using acoustic-phonetic information,' Ph.d. thesis, Computer Science and Engineering, Oregon Graduate Institute of Science and Technology, May, 2000
  6. J. R. Class, 'Finding acoustic regularities in speech : Application to phonetic recognition,' Ph.D. Thesis, MIT Press, May, 1988
  7. K. Kvale, 'On the connection between mannual segmentation conventions and error made by automatic segmentation,' Proceedings of ICSLP'94 (Yokohama, Japan), pp.1667-1670, September, 1994
  8. P. Cosi, 'SLAM : A PC-based multi-level segmentation tool, Speech Recognition and Coding : New Advances and Trends (A. J. R. Ayuso and J. M. L. Soler, eds.),' Computer and System Sciences, Vol.147, Springer-Verlag, New York, pp.124-127, 1995
  9. R. Andre-Obrecht, 'A new statistical approach for the automatic segmentation of continuous speech signals,' IEEE Trans. ASSP 36, pp.29-40, 1988 https://doi.org/10.1109/29.1486
  10. S. Cox, R. Brady, and P. Jackson, 'Techniques for accurate automatic annotation of speech wave forms,' Proceedings of ICSLP'98 (Sydney, Australia), pp.1947-1950, December, 1998
  11. 'http://htk.eng.cam.ac.uk,' Hidden Markov Model Tool Kit Homepage