DocumentCode :
3546849
Title :
Application of denoising algorithm based on LPSO-WNN in speech recognition
Author :
Longfu Zhou ; Yonghe Hu ; Shiyi Xiahou ; Wei Zhang ; Chaoqun Zhang ; Zheng Li ; Dapeng Hao
Author_Institution :
Dept. of Med. Eng., Gen. Hosp. of Chengdu, Chengdu, China
Volume :
2
fYear :
2013
fDate :
15-17 Nov. 2013
Firstpage :
347
Lastpage :
349
Abstract :
This paper introduces an intelligent evaluation method based on improved PSO-WNN (partiele swarm optimization-wavelet neural network) for speech denoising in high background noise. Firstly, by using Lyapunov stability theory, the convergence conditions for single particle in PSO algorithm are discussed and a new strategy based on the result is introduced to improve the performance of PSO algorithm. Then, LPSO-WNN is introduced, in which the improved PSO algorithm is used to optimize the parameters of WNN. Finally, the trained LPSO-WNN is used to identify and recognition the speech signal in high background noise. Experimental results show that the new method is high efficient and practicable for filtering the high background noise and recognition the speech signal.
Keywords :
Lyapunov methods; particle swarm optimisation; signal denoising; speech recognition; wavelet neural nets; LPSO WNN; Lyapunov stability theory; denoising algorithm; high background noise; intelligent evaluation method; particle swarm optimization; speech denoising; speech recognition; speech signal; wavelet neural network; Neural networks; Noise; Noise measurement; Speech; Speech processing; Speech recognition; Training;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Communications, Circuits and Systems (ICCCAS), 2013 International Conference on
Conference_Location :
Chengdu
Print_ISBN :
978-1-4799-3050-0
Type :
conf
DOI :
10.1109/ICCCAS.2013.6765353
Filename :
6765353
Link To Document :
بازگشت