Please use this identifier to cite or link to this item:
https://doi.org/10.1155/ASP.2005.1382
Title: | A two-channel training algorithm for hidden markov model and its application to lip reading | Authors: | Dong, L. Foo, S.W. Lian, Y. |
Keywords: | Discriminative training Separable-distance function Two-channel hidden markov model Viseme recognition |
Issue Date: | 1-Jun-2005 | Citation: | Dong, L., Foo, S.W., Lian, Y. (2005-06-01). A two-channel training algorithm for hidden markov model and its application to lip reading. Eurasip Journal on Applied Signal Processing 2005 (9) : 1382-1399. ScholarBank@NUS Repository. https://doi.org/10.1155/ASP.2005.1382 | Abstract: | Hidden Markov model (HMM) has been a popular mathematical approach for sequence classification such as speech recognition since 1980s. In this paper, a novel two-channel training strategy is proposed for discriminative training of HMM. For the proposed training strategy, a novel separable-distance function that measures the difference between a pair of training samples is adopted as the criterion function. The symbol emission matrix of an HMM is split into two channels: a static channel to maintain the validity of the HMM and a dynamic channel that is modified to maximize the separable distance. The parameters of the two-channel HMM are estimated by iterative application of expectation-maximization (EM) operations. As an example of the application of the novel approach, a hierarchical speaker-dependent visual speech recognition system is trained using the two-channel HMMs. Results of experiments on identifying a group of confusable visemes indicate that the proposed approach is able to increase the recognition accuracy by an average of 20% compared with the conventional HMMs that are trained with the Baum-Welch estimation. © 2005 Hindawi Publishing Corporation. | Source Title: | Eurasip Journal on Applied Signal Processing | URI: | http://scholarbank.nus.edu.sg/handle/10635/54835 | ISSN: | 11108657 | DOI: | 10.1155/ASP.2005.1382 |
Appears in Collections: | Staff Publications |
Show full item record
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.