Title :
Adaptive spatiotemporal neural network for speech recognition
Author :
Wang, Jung-Hua ; Lin, Jia-Hon
Author_Institution :
Dept. of Electr. Eng., Nat. Taiwan Ocean Univ., Keelung, Taiwan
Abstract :
An adaptive spatiotemporal neural network (ASTNN) capable of performing a near Bayesian speech recognizer is proposed. A tuning algorithm is introduced in the ASTNN to adjust the threshold parameters in order to maximize the discrimination distance between competing patterns. The highly confusable English E-set (b, c, d, e, g, p, t, v, z) is used to demonstrate the efficiency of the ASTNN. We show that the recognition rate can reach 80% for single-speaker and 68% for multispeaker respectively
Keywords :
Bayes methods; neural nets; optimisation; speech recognition; ASTNN; English E-set; adaptive spatiotemporal neural network; discrimination distance maximization; near-Bayesian speech recognition; threshold parameter adjustment; Adaptive systems; Bayesian methods; Councils; Electronic mail; Matched filters; Neural networks; Neurons; Oceans; Spatiotemporal phenomena; Speech recognition;
Conference_Titel :
Neural Networks, 1995. Proceedings., IEEE International Conference on
Conference_Location :
Perth, WA
Print_ISBN :
0-7803-2768-3
DOI :
10.1109/ICNN.1995.488191
