Title :
Phoneme recognition with a time-delay neural network
Author :
Shaw, Arnab ; Mitchell, Richard A.
Abstract :
A time-delay neural network architecture is used for speaker-dependent recognition of the long vowel sounds a, e, and i. The following areas are investigated: increasing the amount of data supplied to the network, allowing longer and variable-length utterances, and using English rather than Japanese speech. With this architecture, 100% recognition has been obtained for a population of six speakers
Keywords :
neural nets; parallel architectures; speech recognition; English; Japanese speech; long vowel sounds; phoneme recognition; speaker-dependent recognition; time-delay neural network; variable-length utterances;
Conference_Titel :
Neural Networks, 1990., 1990 IJCNN International Joint Conference on
Conference_Location :
San Diego, CA, USA
DOI :
10.1109/IJCNN.1990.137715
