Improved vector quantization approach for discrete HMM speech recognition system
Joint Authors
Debyeche, Muhammad
Paul Haton, jean
Houacine, Amrane
Source
The International Arab Journal of Information Technology
Issue
Vol. 4, Issue 4 (31 Oct. 2007), pp.338-344, 7 p.
Publisher
Publication Date
2007-10-31
Country of Publication
Jordan
No. of Pages
7
Main Subjects
Information Technology and Computer Science
Topics
Abstract EN
The paper presents an improved Vector Quantization (VQ) approach for discrete Hidden Markov Models (HMMs).
This improved VQ approach performs an optimal distribution of VQ codebook components on HMM states.
This technique, that we named the Distributed Vector Quantization (DVQ) of hidden Markov models, succeeds in unifying acoustic micro-structure and phonetic macro-structure when the estimation of HMM parameters is performed.
The DVQ technique is implemented through two variants ; the first variant uses the K-means algorithm (K-means-DVQ) to optimize the VQ, while the second variant exploits the benefits of the classification behavior of Neural Networks (NN-DVQ) for the same purpose.
The proposed variants are compared with the HMM-based baseline system by experiments of specific Arabic consonants recognition.
The results show that the distributed vector quantization technique increase the performance of the discrete HMM system while maintaining the decoding speed of the models.
American Psychological Association (APA)
Debyeche, Muhammad& Paul Haton, jean& Houacine, Amrane. 2007. Improved vector quantization approach for discrete HMM speech recognition system. The International Arab Journal of Information Technology،Vol. 4, no. 4, pp.338-344.
https://search.emarefa.net/detail/BIM-11725
Modern Language Association (MLA)
Houacine, Amrane…[et al.]. Improved vector quantization approach for discrete HMM speech recognition system. The International Arab Journal of Information Technology Vol. 4, no. 4 (Oct. 2007), pp.338-344.
https://search.emarefa.net/detail/BIM-11725
American Medical Association (AMA)
Debyeche, Muhammad& Paul Haton, jean& Houacine, Amrane. Improved vector quantization approach for discrete HMM speech recognition system. The International Arab Journal of Information Technology. 2007. Vol. 4, no. 4, pp.338-344.
https://search.emarefa.net/detail/BIM-11725
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references : p. 344
Record ID
BIM-11725