Using localized basis function for multi-speaker speech recognition

Author

Chen, Dao Wen

Author_Institution

Inst. of Autom., Acad. Sinica, Beijing, China

fYear

1994

fDate

13-16 Apr 1994

Firstpage

734

Abstract

In this paper, a localized basis function neural network is suggested to perform a mathematical mapping to give a desired output vector in response to the input vector. This paper studied the mapping accuracy and convergence performance and discussed the key point of how to determine both the location and the number of the basis function, and the other key point of deciding the width of the receptive field of basis function. As an example, by way of speaker´s voice mapping, a specific radial basis function net is presented for multi-speaker speech recognition and the error rate reduced to 75% compared to the original model

Keywords

convergence of numerical methods; feedforward neural nets; learning (artificial intelligence); speech recognition; convergence performance; error rate; input vector; localized basis function; mapping accuracy; mathematical mapping; multi-speaker speech recognition; neural network; output vector; radial basis function net; speaker´s voice mapping; Covariance matrix; Databases; Function approximation; Hidden Markov models; Neural networks; Pattern recognition; Speech recognition; Text recognition; Vectors; Vocabulary;

fLanguage

English

Publisher

ieee

Conference_Titel

Speech, Image Processing and Neural Networks, 1994. Proceedings, ISSIPNN '94., 1994 International Symposium on

Print_ISBN

0-7803-1865-X

Type

conf

DOI

10.1109/SIPNN.1994.344807

Filename

344807