First European Conference on Speech Communication and Technology

Paris, France
September 27-29, 1989

Analysis of a Neural Network Model for Speech Recognition

Steve Renals (1,2), Jonathan Dalby (2)

(1) Department of Physics, University of Edinburgh
(2) Centre for Speech Technology Research, University of Edinburgh, Edinburgh, Scotland, UK

An analysis of a feed-forward neural network model performing a vowel recognition task is reported. Two experiments analysed in detail involved training on speech processed using linear prediction and the discrete FFT. A phonetic analysis of the resultant weight matrices is offered, additionally we analyse the network structure using pairwise correlations and principal components analysis. We suggest methods of network initialisation obtained by inverting these analyses.

Full Paper

Bibliographic reference.  Renals, Steve / Dalby, Jonathan (1989): "Analysis of a neural network model for speech recognition", In EUROSPEECH-1989, 1333-1336.