Affiliation:
1. CISCO School of Informatics,Guangdong University of Foreign Studies
2. School of Business Adminstrtion, South China University of Technology
Abstract
A probabilistic neural network (PNN) speech recognition model based on the partition clustering algorithm is proposed in this paper. The most important advantage of PNN is that training is easy and instantaneous. Therefore, PNN is capable of dealing with real time speech recognition. Besides, in order to increase the performance of PNN, the selection of data set is one of the most important issues. In this paper, using the partition clustering algorithm to select data is proposed. The proposed model is tested on two data sets from the field of spoken Arabic numbers, with promising results. The performance of the proposed model is compared to single back propagation neural network and integrated back propagation neural network. The final comparison result shows that the proposed model performs better than the other two neural networks, and has an accuracy rate of 92.41%.
Publisher
Trans Tech Publications, Ltd.
Reference11 articles.
1. D. F. Specht. Probabilistic neural networks., Neural Networks, 1(3): 109-118. (1990).
2. Bulent Bolat and Tulay Yildirim. Performance Increasing Methods for Probabilistic Neural Networks. Pakistan Journal of Information and Technology , 2 (3): 250-255, (2003).
3. D.F. Specht, Enhancements to Probabilistic Neural Networks, InternationalJoint Conference on Neural Networks, vol. I, pp.761-768, June (1992).
4. B. Bolat and T. Yildirim. A data selection method for probabilistic neural networks. In XII International Turkish Symposium on Artificial Intelligence and Neural Networks TAINN'2003, (2003).
5. Fabio Ancona, Anna Maria Colla, Stefano Rovetta, and Rodolfo Zunino. Implementing probabilistic neural networks. Neural Comput & Applic (1998)7: 37-51 , (1998).