Abstract
The authors describe 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 domain 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. The first model performs a spectral analysis of the input speech signal. The second model is a self-structuring neural noise reduction (SNNR) model. The noise reduced output from the SNNR network is propagated through the speech recognizer consisting of a set of hidden control neural networks (HCNN)
Original language | English |
---|---|
Title of host publication | EUROSPEECH 91 |
Publication date | 1990 |
Publication status | Published - 1990 |
Externally published | Yes |
Event | ESCA Proceedings European Conference on Speech Communication and Technology - Genova, Italy Duration: 1 Jan 1991 → … |
Conference
Conference | ESCA Proceedings European Conference on Speech Communication and Technology |
---|---|
City | Genova, Italy |
Period | 01/01/1991 → … |