Isolated Word Recognition Using Ergodic Hidden Markov Models and Genetic Algorithm
Abstract
Speech to text was one of speech recognition applications which speech signal was processed, recognized and converted into a textual representation. Hidden Markov model (HMM) was the widely used method in speech recognition. However, the level of accuracy using HMM was strongly influenced by the optimalization of extraction process and modellling methods. Hence in this research, the use of genetic algorithm (GA) method to optimize the Ergodic HMM was tested. In Hybrid HMM-GA, GA was used to optimize the Baum-Welch method in the training process. It was useful to improve the accuracy of the recognition result which is produced by the HMM parameters that generate the low accuracy when the HMM are tested. Based on the research, the percentage increases the level of accuracy of 20% to 41%. Proved that the combination of GA in HMM method can gives more optimal results when compared with the HMM system that not combine with any method.
Full Text:
PDFReferences
S Kwong, Chau W. Analysis of Parallel Genetic Algorithms on HMM Based Speech Recognition System. City University of Hong Kong. IEEE Transactions on Consumer Electronics. 1997; 43(4)
Glass J. Introduction to Automatic Speech Recognition. 2003.
Cho SJ. Introduction to Hidden Markov Model and Its Application. Samsung Advanced Institute of Technology (SAIT). 2005.
Shing-Tai P, Ching-Fa C, Jian-Hong Z. Speech Recognition via Hidden Markov Model and Neural Network Trained by Genetic Algorithm. Ninth International Conference on Machine Learning and Cybernetics. Qingdao, 11-14 July 2010.
SA Selouani, D O’Shaughnessy. Robustness of Speech Recognition Using Genetic Algorithms and A Mel-Cepstral Subspace Approach. IEEE Transactions on Neural Network. 2004.
Shing-Tai P, hih-Hung W, Shih-Chin L. The Application of Improved Genetic Algorithm on The training of Neural Network for Speech Recognition. IEEE Transactions on Neural Network. 2007.
Bhaskar MM, Maheswarapu S. A Hybrid Genetic Algorithm Approach for Optimal Power Flow. TELKOMNIKA. 2011; 9(2): 211-216.
Cernock J. Speech Recognition Based on Hidden Markov Models. Brno University of Technology. 2007.
Terry L. Ergodic Hidden Markov Models for Visual-Only Isolated Digit Recognition. Dissertation. Electical Engineering Northwestern University: Evanston, Illinois. 2007.
Rabiner LJ, Biing-Hwang. Fundamentals of Speech Recognition. Prentice Hall International Edition.1993.
Xueying Z, Yiping W, Zhefeng Z. A Hybrid Speech Recognition Training Method for HMM Based on Genentic Algorithm and Baum Welch Algorithm. IEEE Transactions on Neural Network. 2007.
Mourad O, Raja NA. HMM Parameters Estimation Using Hybrid. IEEE. 2010.
Chu SH. Combination of GA and SDM to Improve ANN Training Effiiency. Shu-Te University. MS Thesis. 2003.
Preetham S, Kedar N, Lakshmi. Speech Recognition using HMMs. IIIT-Hyderabad. 2003.
Jain AK, Duin RPW, Mao J. Statistical Pattern Recognition: A Review. IEEE Transaction on Pattern Analysis and Machine Intelligence. 2000.
Kim FM, Tang KS, Kwong S. Genetic Algortihm: Concept and Design. Springer. 2001.
Sutikno T, Facta M, Markadeh GRA. Progress in Artificial Intelligence Techniques: from Brain to Emotion. TELKOMNIKA. 2011; 9(2): 201-202.
Lan ML, Pan ST, Lai CC. Using Genetic Algorithm to Improve the Performance of Speech Recognition Based on Artificial Neural Network. Dept.of Computer Science and Information Engineering, Shu-Te University Taiwan. Proceesings of the First International on Innovative Computing, Information and Control (ICICIC’06).
DOI: http://doi.org/10.12928/telkomnika.v10i1.769
Refbacks
- There are currently no refbacks.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
TELKOMNIKA Telecommunication, Computing, Electronics and Control
ISSN: 1693-6930, e-ISSN: 2302-9293
Universitas Ahmad Dahlan, 4th Campus
Jl. Ringroad Selatan, Kragilan, Tamanan, Banguntapan, Bantul, Yogyakarta, Indonesia 55191
Phone: +62 (274) 563515, 511830, 379418, 371120
Fax: +62 274 564604