Recurrent neural network speech predictor based on dynamical systems approach

A nonlinear predictive model of speech, based on the method of time delay reconstruction, is presented and approximated using a fully connected recurrent neural network (RNN) followed by a linear combiner. This novel combination of the well established approaches for speech analysis and synthesis is compared with traditional techniques within a unified framework to illustrate the advantages of using an RNN. Extensive simulations are carried out to justify the expectations. Specifically, the network´s robustness to the selection of reconstruction parameters, the embedding time delay and dimension, is intuitively discussed and experimentally verified. In all cases, the proposed network was found to be a good solution for both prediction and synthesis