Monthly
288 pp. per issue
6 x 9, illustrated
ISSN
0899-7667
E-ISSN
1530-888X
2014 Impact factor:
2.21

Neural Computation

January 1992, Vol. 4, No. 1, Pages 108-119
(doi: 10.1162/neco.1992.4.1.108)
© 1992 Massachusetts Institute of Technology
Speaker-Independent Digit Recognition Using a Neural Network with Time-Delayed Connections
Article PDF (700.6 KB)
Abstract

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 speaker-independent setting, many new ideas and procedures were developed. These include improving the feature detectors, self-recognition of word ends, reduction in network size, and dividing speakers into natural classes. Quantitative experiments based on Texas Instruments (TI) digit databases are described.