The standard support vector machine (SVM) is a common method of machine learning, the parameters selection of SVM affects the machine learning ability directly. At present, the research on the choice of SVM parameters is still no uniform approach. In order to avoid the difficult problem of selecting parameters, this paper used a deformed SVM, that is, v-SVM, selected parameters of v-SVM by particle swarm optimization algorithm, and used the optimized parameters in a non-specific persons, isolated words, medium-vocabulary speech recognition system. The experimental results show that this optimizing v-SVM parameters method gets better speech recognition correct rates than general parameters selection ways in different signal to noise ratios and different words. So the method is effective feasible, the optimized parameters make v-SVM have good generalization, the speech recognition results and convergence rate have been improved.
[1]
Chih-Jen Lin,et al.
Training v-Support Vector Classifiers: Theory and Algorithms
,
2001,
Neural Computation.
[2]
Gang Peng,et al.
Tone recognition of continuous Cantonese speech based on support vector machines
,
2005,
Speech Commun..
[3]
Russell C. Eberhart,et al.
A new optimizer using particle swarm theory
,
1995,
MHS'95. Proceedings of the Sixth International Symposium on Micro Machine and Human Science.
[4]
Dong Wang.
Utilizing particle swarm optimization to optimize hyper-parameters of SVM classifier: Utilizing particle swarm optimization to optimize hyper-parameters of SVM classifier
,
2008
.