Arabic phonetic features recognition using modular connectionist architectures

This paper proposes an approach for reliably identifying complex Arabic phonemes in continuous speech. This is proposed to be done by a mixture of artificial neural experts. These experts are typically time delay neural networks using an original version of the autoregressive backpropagation algorithm (AR-TDNN). A module using specific cues generated by an ear model operates the speech phone segmentation. Perceptual linear predictive (PLP) coefficients, energy, zero crossing rate and their derivatives are used as input parameters. Serial and parallel architectures of AR-TDNN have been implemented and confronted to a monolithic system using a simple backpropagation algorithm