DocumentCode :
2721427
Title :
Improving a phoneme classification neural network through problem decomposition
Author :
Pratt, L.Y. ; Kamm, C.A.
Author_Institution :
Dept. of Comput. Sci., Rutgers Univ., New Brunswick, NJ, USA
fYear :
1991
fDate :
8-14 Jul 1991
Firstpage :
821
Abstract :
The authors discuss how a methodology called problem decomposition can be applied to an AP-net, a neural network for mapping acoustic spectra to phoneme classes. The network´s task is to recognize phonemes from a large corpus of multiple-speaker, continuously spoken sentences. The authors review previous AP-net systems and present results from a decomposition study in which smaller networks trained to recognize subsets of phonemes are combined into a larger network for the full signal-to-phoneme mapping tasks. It is shown that, by using this problem decomposition methodology, comparable performance can be obtained in significantly fewer arithmetic operations
Keywords :
neural nets; speech recognition; AP-net; continuously spoken sentences; mapping acoustic spectra; phoneme classes; phoneme classification neural network; problem decomposition; signal-to-phoneme mapping tasks; Arithmetic; Artificial intelligence; Computer science; Data preprocessing; Neural networks; Performance evaluation; Search problems; Signal mapping; Speech; Testing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 1991., IJCNN-91-Seattle International Joint Conference on
Conference_Location :
Seattle, WA
Print_ISBN :
0-7803-0164-1
Type :
conf
DOI :
10.1109/IJCNN.1991.155440
Filename :
155440
Link To Document :
بازگشت