Browse > Article

Clustering In Tied Mixture HMM Using Homogeneous Centroid Neural Network  

Park Dong-Chul (명지대학교 정보공학과 지능컴퓨팅 연구실)
Kim Woo-Sung (호서대학교 컴퓨터공학부)
Publication Information
The Journal of Korean Institute of Communications and Information Sciences / v.31, no.9C, 2006 , pp. 853-858 More about this Journal
Abstract
TMHMM(Tied Mixture Hidden Markov Model) is an important approach to reduce the number of free parameters in speech recognition. However, this model suffers from a degradation in recognition accuracy due to its GPDF (Gaussian Probability Density Function) clustering error. This paper proposes a clustering algorithm, called HCNN(Homogeneous Centroid Neural network), to cluster acoustic feature vectors in TMHMM. Moreover, the HCNN uses the heterogeneous distance measure to allocate more code vectors in the heterogeneous areas where probability densities of different states overlap each other. When applied to Korean digit isolated word recognition, the HCNN reduces the error rate by 9.39% over CNN clustering, and 14.63% over the traditional K-means clustering.
Keywords
Speech Recognition; Tied Mixture; Unsupervised Learning; Hidden Markov Model;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Dermatas, E. and Kokkinakis, G., 'Algorithm for clustering continuous density HMM by recognition error', IEEE Tr. on ASSP, vol.4, pp231-234, May. 1996
2 박동철, 우영준, '신경망에의한 테두리를 보존하는 영상압축,' 한국통신학회 논문지, 24권, 10B호, pp. 1946-1952, 1999
3 Park, D.C., Kwon, D.H., and Suk, M., 'Clustering of Gaussian Probability Density Functions Using Centroid Neural Networks,' IEE Electronic Letters, vol 49, no.4, pp.381-382, Feb 2003
4 Park, D.C., 'Centroid Neural Network for Unsupervised Competitive Learning', IEEE Tr. on Neural Networks, vol. 11, no.2, pp520-528, Mar. 2000   DOI   ScienceOn
5 Rigazio, L., Tsakam B., and Junqua J., 'An optimal Bhattacharyya centroid algorithm for Gaussian clustering with applications in automatic speech recognition,' Proc. of ICASSP, vol.3, pp. 1599-1602, 2000
6 Liu, Y. and Fung, P., 'State dependent phonetic tied mixtures with pronunciation modeling for spontaneous speech recognition,' IEEE Tr. on ASSP, vol.14, issue. 1, pp. 89-102, Jul. 2004