Cooperative supervised and unsupervised learning algorithm for phoneme recognition in continuous speech and speaker-independent context

Abstract

Neural networks have been traditionally considered as an alternative approach to pattern recognition in general, and speech recognition in particular. There have been much success in practical pattern recognition applications using neural networks including multi-layer perceptrons, radial basis functions, and self-organizing maps (SOMs). In this paper, we propose a system of SOMs based on the association of some supervised and unsupervised learning algorithms inherited from the most popular neural network in the unsupervised learning category, SOM. The case study of the proposed system of SOMs is phoneme recognition in continuous speech and speaker independent context. Also, we propose a way to save more information during training phase of a Kohonen map in the objective to ameliorate speech recognition accuracy. The applied SOM variants serve as tools for developing intelligent systems and pursuing artificial intelligence applications.