Title :
Evaluation of segmental unit input HMM
Author :
Nakagawa, Seiichi ; Yamamoto, Kazumasa
Author_Institution :
Dept. of Inf. & Comput. Sci., Toyohashi Univ. of Technol., Japan
Abstract :
The standard HMM cannot fully express the time variant features while staying at the same state. So as not to ignore the dynamic changes of the speech characteristics, various methods have been studied. In this paper, we compare a segmental unit input HMM where several successive frames are combined and become an input vector, with conditional density HMM or the use of regression coefficients and evaluate them. Using segmental statistics, since the dimension of the parameters increases, results in a lesser precision in estimation of the covariance matrix. Therefore we used methods for compressing dimension and reducing computation by K-L expansion and MQDF. By segmental unit inputting for the basic structure HMM, we got a better recognition rate than by traditional methods and the combination of a segmental unit of successive mel-cepstrum frames and regression coefficients showed the best recognition rate
Keywords :
cepstral analysis; computational complexity; covariance matrices; hidden Markov models; speech recognition; statistical analysis; transforms; K-L expansion; MQDF; computation; conditional density HMM; covariance matrix; dimension; dynamic changes; input vector; recognition rate; regression coefficients; segmental statistics; segmental unit input HMM; speech characteristics; successive frames; successive mel-cepstrum frames; time variant features; Cepstrum; Covariance matrix; Hidden Markov models; Linear discriminant analysis; Linear regression; Predictive models; Speech coding; Statistics; Vectors; Yttrium;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1996. ICASSP-96. Conference Proceedings., 1996 IEEE International Conference on
Conference_Location :
Atlanta, GA
Print_ISBN :
0-7803-3192-3
DOI :
10.1109/ICASSP.1996.541127