Second European Conference on Speech Communication and Technology

Genova, Italy
September 24-26, 1991


A Self-Structuring Neural Noise Reduction Model

Helge B. D. Sorensen, Uwe Hartmann

Speech Technology Centre, Institute of Electronic Systems, University of Aalborg, Aalborg, Denmark

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 approximates 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 [1]. 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 [1] presented at ICASSP91. The noise reduced output from the SNNR network is propagated through the speech recognizer consisting of a set of Hidden Control Neural Networks (HCNN).

Full Paper

Bibliographic reference.  Sorensen, Helge B. D. / Hartmann, Uwe (1991): "A self-structuring neural noise reduction model", In EUROSPEECH-1991, 567-570.