Title :
Recognition of consonant based on the perceptron model
Author :
Makino, Shozo ; Kawabata, Takeshi ; Kido, Keniti
Author_Institution :
Tohoku University
Abstract :
This paper proposes a new method for the recognition of consonant based on the Perceptron model. The recognition model is composed of the sensory, feature extraction, response and lateral inhibition layers. The recognition scores of 90.4% to 98.4% are obtained for unvoiced affricates, unvoiced plosives, unvoiced and voiced fricatives.
Keywords :
Band pass filters; Feature extraction; Finite impulse response filter; Frequency; Logic; Physics computing; Power system modeling; Speech analysis; Speech recognition; Vectors;
Conference_Titel :
Acoustics, Speech, and Signal Processing, IEEE International Conference on ICASSP '83.
DOI :
10.1109/ICASSP.1983.1172080
