Speaker-Independent Digit Recognition Using a Neural Network with Time-Delayed Connections
Keyword(s):
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.
Keyword(s):
Keyword(s):
2019 ◽
Vol 29
(9)
◽
pp. 091101
◽
Keyword(s):
Keyword(s):