Speaker-Independent Digit Recognition Using a Neural Network with Time-Delayed Connections

K. P. Unnikrishnan, J. J. Hopfield, D. W. Tank
1992 Neural Computation  
The capability of a small neural network to perform speaker-independent recognition of spoken digits in connected speech has been investigated. The network uses time delays to organize rapidly changing outputs of symbol detectors over the time scale of a word. The network is data driven and unclocked. To achieve useful accuracy in a speakerindependent setting, many new ideas and procedures were developed. These include improving the feature detectors, self-recognition of word ends, reduction in
more » ... ends, reduction in network size, and dividing speakers into natural classes. Quantitative experiments based on Texas Instruments (TI) digit data bases are described.
doi:10.1162/neco.1992.4.1.108 fatcat:sgaelftzqnfifgpf62dbfkjw4e