Noisy speech recognition by hierarchical recurrent neural fuzzy networks

Author

Juang, Chia-Feng ; Chiou, Chyi-Tian ; Huang, Hao-Jung

Author_Institution

Dept. of Electr. Eng., Nat. Chung-Hsing Univ., Taichung, Taiwan

fYear

2005

fDate

23-26 May 2005

Firstpage

5122

Abstract

Noisy speech recognition by hierarchical recurrent neural fuzzy networks (HRNFN) is proposed. The proposed HRNFN is a hierarchical connection of two recurrent neural fuzzy networks, where one is used for noise filtering and the other for recognition. The recurrent neural fuzzy network used is the TSK-type recurrent fuzzy network (TRFN), which is constructed by recurrent fuzzy if-then rules. In n words recognition, n TRFNs are created for n words modeling. The total prediction error of each TRFN is used as recognition criterion. In filtering, n TRFNs are created, and each TRFN recognizer is connected with a corresponding TRFN filter, which filters noisy speech patterns in the feature domain before feeding them to the recognizer. Experiments on words recognition under different types of noise are performed to verify the performance of HRNFN.

Keywords

acoustic noise; fuzzy neural nets; nonlinear filters; random noise; recurrent neural nets; speech recognition; hierarchical recurrent neural fuzzy networks; noise filtering; noisy speech pattern filtering; noisy speech recognition; nonlinear filter; prediction error; recognition criterion; recurrent fuzzy if-then rules; recurrent fuzzy network; word modeling; word recognition; Automatic speech recognition; Degradation; Filtering; Fuzzy neural networks; Nonlinear filters; Pattern recognition; Recurrent neural networks; Signal to noise ratio; Speech recognition; Working environment noise; Speech recognition; nonlinear filter; recurrent fuzzy network; recurrent neural network;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 2005. ISCAS 2005. IEEE International Symposium on

Print_ISBN

0-7803-8834-8

Type

conf

DOI

10.1109/ISCAS.2005.1465787

Filename

1465787