Browse > Article

Efficient context dependent process modeling using state tying and decision tree-based method  

Ahn, Chan-Shik (광운대학교 컴퓨터공학과)
Oh, Sang-Yeob (경원대학교 IT대학 컴퓨터미디어)
Publication Information
Journal of Korea Multimedia Society / v.13, no.3, 2010 , pp. 369-377 More about this Journal
Abstract
In vocabulary recognition systems based on HMM(Hidden Markov Model)s, training process unseen model bring on show a low recognition rate. If recognition vocabulary modify and make an addition then recreated modeling of executed database collected and training sequence on account of bring on additional expenses and take more time. This study suggest efficient context dependent process modeling method using decision tree-based state tying. On study suggest method is reduce recreated of model and it's offered that robustness and accuracy of context dependent acoustic modeling. Also reduce amount of model and offered training process unseen model as concerns context dependent a likely phoneme model has been used unseen model solve the matter. System performance as a result of represent vocabulary dependence recognition rate of 98.01%, vocabulary independence recognition rate of 97.38%.
Keywords
vocabulary recognition; speech database; decision tree; independence vocabulary;
Citations & Related Records
Times Cited By KSCI : 4  (Citation Analysis)
연도 인용수 순위
1 S. Young, D. Kershaw, J Odell, D. Ollason, Valtcher, P. Woodland, "The HTK Book," Cambridge University Engineering Department, 2002.
2 방기덕, 강철호,"가변 신뢰도 문턱치를 사용한 미등록어 거절 알고리즘에 대한 연구," 멀티 미디어학회논문지, Vol. 11, No. 11, pp. 1471-1479, 2008. 11.   과학기술학회마을
3 W. Daelemans, S. Buchholz, and J. Veenstra, "Memorybased shallow parsing," in Proc CoNLL, pp. 53-60, 1999.
4 W. Reichl and W. chou, "Decision Tree State Tying Based on Segmental Clustering for Acoustic Modeling," Proc ICASSP, Seattle, pp. 801-804, 1998.
5 M. F. Gales, "Model- based techniques for nosie robust speech recognition," Ph. D. dissertation, University of Cambridge, Sept, 1995.
6 D. Jurafsky and J. H. Martin, "Speech and Language Processing," Prentice- Hall, 2000.
7 김동주, 김한우, "문맥가중치가 반영된 문장 유사도 척도," 전자공학회논문지, 제43권 6호, pp.496-504, 2006.   과학기술학회마을
8 T. jitsuhiro, S. Takatoshi, and K. Aikawa, "Rejection of out-of-vocabulary words using phoneme confidence likelihood," ICASSP, pp. 217-220, 1998.
9 Herry F. Korth, Abraham Silberschat,. Database system concepts, 1991.
10 Tichy, W. F., "Rcs-A System for Version Control," Software Practice & Experience, Vol.15 No.7, pp. 637-654, 1985.   DOI   ScienceOn
11 Hyoungjoo Kim, and Henery F. Korth. Schema Version and View a in Object-ori-ented Database. Proc. INFO JAPAN. 1990.
12 Agrawal, R. Buroff, S., Gehani, N. and Shasha, D "Object Versioning in code," processing of 7th International Conference on Data Engineering, pp. 446-455, 1991.
13 김덕현, 박성주,"확장된 객체지향데이터 모형을 이용한 소프트웨어 변경관리 시스템," 정보과학회논문지, Vol.22, No.2. pp. 249-260, 1995.
14 Keith E. Gorlen "An Object-Oriented Class Library for C++ Program," Software-Practice and Experience. Vol.17, No.12. pp. 899-922. 1987.   DOI   ScienceOn
15 박서영, 김갑수, 명선영, 신영길, 우치수, "객체지향 패러다임에서의 소프트웨어 컴포넌트 분류에 관한 연구," 정보과학회논문지, Vol.20, No.2, pp. 879- 882. 1993.
16 R. Helm, Y. S. Maarek, "Integrating Information Retrieval and Domain Specific Approaches for Browsing and Retrieval in Object Oriented Class Libraries," Proceeding of OOPSLA'91, pp. 47-61, 1991.
17 L. Rabiner, B. H. Juang, "Fundamentals of speech recognition," Prentice Hall, 1993.
18 L. R. Bahl, P. V. deSouza, P. S. Gopalarishnan, D. Nahamoo, and M. Picheny, "A Fast Match for Continuous Speech Recognition Using Allophonic Models," In Proc. IEEE ICASSP-92, Vol.1, pp. 17- 21, 1992.
19 A. S. Manos and V. W. Zue, "A study on ou-tof- vocabulary word modeling for a segment-based keyword spotting system," Master Thesis, MIT, 1996.
20 안태옥, "혼합 가우시안 군집화를 이용한 상태공유 음향모텔 최적화," 전자공학회논문지, 제42권 SP편 제6호, pp. 167-176, 2005. 11.   과학기술학회마을
21 신광호, 정호열, 정현열, "음성 개선 기반의 모델 보상 기법을 이용한 강인한 잡음 음성 인식," 음향학회 논문지, Vol.27, No.4, pp. 191-199, 2008. 5.   과학기술학회마을