Speech Recognition Neural Methods in E-learning Environments

In the learning process, and even more in e-learning environments, communication is very important. But there are certain situations with persons that can give only voice commands. In this case, the classical techniques for e-learning must be improved with methods based on automatic speech recognition (ASR). In this paper we present a case study of phonemes recognition for Romanian language, starting with speech signal analysis, and continuing with most used techniques for ASR, artificial neural networks. Finally, the results of the experiments are presented.