Continuous speech recognition by adaptive temporal radial basis function

This work presents the adaptive temporal radial basis function "ATRBF" applied to continuous speech recognition, in particular the recognition of phonemes. ATRBF combines features from time delay neural network "TDNN" and the advantages of radial basis function "RBF". The capacity to detect the acoustic features and their independent temporal report of the temporal localisation is inspired from the TDNN model. The main use of radial basis functions is both their speed of treatment and few parameters to adjust for the training phase, which encourages applying this model to new tasks in most delicate cases. The algorithm automatically selects the significant RBF centres and estimates the weights and delay at the same time. The adaptability is obviously when applying this approach in speech recognition, especially for phoneme recognition. This resemble to what would make a human brain in like situation.