A prototype isolated-word recognizer was constructed, with an auditory-based analysis component and a pattern classification module based on a parallel distributed processing paradigm. The auditory model used was a bandpass nonlinear configuration which incorporates the effects of lateral suppression. Pattern classification was performed by a layered, feed-forward neural network, consisting of an array of input nodes representing the binary features output by the auditory model, a set of hidden nodes and an array of output nodes representing the word to be recognized. This prototype recognizer was trained to recognize English digits spoken by male and female speakers. Recognition rates for the digit set (zero to ten) were better than 80%.
|Number of pages||4|
|Journal||ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings|
|Publication status||Published - 1988|