A neural network architecture for speech segmentation using mean field annealing

Author

Jeong, C.G. ; Jeong, H.

Author_Institution

Dept. of Electr. Eng., POSTECH, Pohang, South Korea

Volume

7

fYear

1994

fDate

27 Jun-2 Jul 1994

Firstpage

4442

Abstract

As a dual algorithm to the Geiger-Girosi restoration scheme, a new segmentation method is introduced and used to demonstrate an approach to phoneme boundary detection. Also the authors introduce a neural network suitable for this algorithm, which consists of sigmoid neurons and Sigma-Pi neurons. Experimental results show that the new algorithm is superior to the forward-backward algorithm and the Geiger-Girosi algorithm in terms of position accuracy and recognition accuracy as well as computational speed for phoneme-boundary detection

Keywords

neural net architecture; speech recognition; Geiger-Girosi restoration scheme; Sigma-Pi neurons; computational speed; mean field annealing; neural network architecture; phoneme boundary detection; position accuracy; recognition accuracy; sigmoid neurons; speech segmentation; Annealing; Image restoration; Neural networks; Neurons; Optical signal processing; Signal processing algorithms; Signal restoration; Speech; Testing; Virtual colonoscopy;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on

Conference_Location

Orlando, FL

Print_ISBN

0-7803-1901-X

Type

conf

DOI

10.1109/ICNN.1994.374985

Filename

374985