Speech recognition in noise using a self-structuring noise reduction model and hidden control models

This paper describes how speech recognition in the presence of F-16 jet cockpit noise can be performed using a sequence of three units - an auditory model and two neural models. A method for noise reduction in the cepstral domian based on a self-structuring universal approximator is proposed and tested on a large database of isolated words contaminated with jet noise. This approach is a potential alternative to traditional recognition methods for noisy speech and makes noise reduction possible in all three models as in the system in [l]. The first model performs a spectral analysis of the input speech signal. The second model is a Self-structuring Neural Noise Reduction (SNNR) model, which is an alternative to the noise reduction model [l] presented at IJCNN91. The noise reduced output from the SNNR network is propagated through the speech recognizer consisting of a set of Hidden Control Neural Networks (HCNN).