GA_FastICA Algorithmfor Speech Separation

With the development of speech processing technology, new speech separation algorithms are constantly proposed. The GA_FastICA algorithm is proposed by combining the Geometric Approach (GA) algorithm and Fast Independent Component Analysis (FastICA) algorithm for the problem of unsatisfactory separa...

Full description

Saved in:
Bibliographic Details
Main Authors: LAN Chao-feng, CHEN Ying-qi, LIN Xiao-jia, LIU Yan, CHEN Xu-qi
Format: Article
Language:zho
Published: Harbin University of Science and Technology Publications 2022-12-01
Series:Journal of Harbin University of Science and Technology
Subjects:
Online Access:https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=2161
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849316348418588672
author LAN Chao-feng
CHEN Ying-qi
LIN Xiao-jia
LIU Yan
CHEN Xu-qi
author_facet LAN Chao-feng
CHEN Ying-qi
LIN Xiao-jia
LIU Yan
CHEN Xu-qi
author_sort LAN Chao-feng
collection DOAJ
description With the development of speech processing technology, new speech separation algorithms are constantly proposed. The GA_FastICA algorithm is proposed by combining the Geometric Approach (GA) algorithm and Fast Independent Component Analysis (FastICA) algorithm for the problem of unsatisfactory separation due to the noise in the observed signal and combining the geometric operation method. The time domain waveforms of the separated speech signals are plotted, and the correlation coefficients of the original and separated speech signals are given to investigate the effectiveness of the GA algorithm.When the signal-to-noise ratio is 4dB, the correlation coefficient of the separated speech signal and the original speech signal is 0.7852 . The experimental simulation results show that under the signal-to-noise ratio of 12dB, factory and babble noise conditions, the GA_FastICA algorithm improves the correlation coefficient by 0.0212 and 0.0304 compared with the FastICA algorithm, and the correlation coefficients were improved by 0.1374 and 0.1328 for a signal-to-noise ratio of 8dB. The GA_FastICA algorithm can effectively separate the speech signal, and the noisy environment GA_FastICA algorithm can effectively separate speech signals and has a better speech separation effect.
format Article
id doaj-art-21009c98df1747f09d222c84a9c0e4fb
institution Kabale University
issn 1007-2683
language zho
publishDate 2022-12-01
publisher Harbin University of Science and Technology Publications
record_format Article
series Journal of Harbin University of Science and Technology
spelling doaj-art-21009c98df1747f09d222c84a9c0e4fb2025-08-20T03:51:48ZzhoHarbin University of Science and Technology PublicationsJournal of Harbin University of Science and Technology1007-26832022-12-012706808710.15938/j.jhust.2022.06.010GA_FastICA Algorithmfor Speech SeparationLAN Chao-feng0CHEN Ying-qi1LIN Xiao-jia2LIU Yan3CHEN Xu-qi4School of Measurement and Communications Engineering, Harbin University of Science and Technology, Harbin 150080,ChinaSchool of Measurement and Communications Engineering, Harbin University of Science and Technology, Harbin 150080,ChinaSchool of Measurement and Communications Engineering, Harbin University of Science and Technology, Harbin 150080,ChinaSchool of Measurement and Communications Engineering, Harbin University of Science and Technology, Harbin 150080,ChinaSchool of Measurement and Communications Engineering, Harbin University of Science and Technology, Harbin 150080,ChinaWith the development of speech processing technology, new speech separation algorithms are constantly proposed. The GA_FastICA algorithm is proposed by combining the Geometric Approach (GA) algorithm and Fast Independent Component Analysis (FastICA) algorithm for the problem of unsatisfactory separation due to the noise in the observed signal and combining the geometric operation method. The time domain waveforms of the separated speech signals are plotted, and the correlation coefficients of the original and separated speech signals are given to investigate the effectiveness of the GA algorithm.When the signal-to-noise ratio is 4dB, the correlation coefficient of the separated speech signal and the original speech signal is 0.7852 . The experimental simulation results show that under the signal-to-noise ratio of 12dB, factory and babble noise conditions, the GA_FastICA algorithm improves the correlation coefficient by 0.0212 and 0.0304 compared with the FastICA algorithm, and the correlation coefficients were improved by 0.1374 and 0.1328 for a signal-to-noise ratio of 8dB. The GA_FastICA algorithm can effectively separate the speech signal, and the noisy environment GA_FastICA algorithm can effectively separate speech signals and has a better speech separation effect.https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=2161speech processingspeech separationindependent component analysissignal to noise ratio
spellingShingle LAN Chao-feng
CHEN Ying-qi
LIN Xiao-jia
LIU Yan
CHEN Xu-qi
GA_FastICA Algorithmfor Speech Separation
Journal of Harbin University of Science and Technology
speech processing
speech separation
independent component analysis
signal to noise ratio
title GA_FastICA Algorithmfor Speech Separation
title_full GA_FastICA Algorithmfor Speech Separation
title_fullStr GA_FastICA Algorithmfor Speech Separation
title_full_unstemmed GA_FastICA Algorithmfor Speech Separation
title_short GA_FastICA Algorithmfor Speech Separation
title_sort ga fastica algorithmfor speech separation
topic speech processing
speech separation
independent component analysis
signal to noise ratio
url https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=2161
work_keys_str_mv AT lanchaofeng gafasticaalgorithmforspeechseparation
AT chenyingqi gafasticaalgorithmforspeechseparation
AT linxiaojia gafasticaalgorithmforspeechseparation
AT liuyan gafasticaalgorithmforspeechseparation
AT chenxuqi gafasticaalgorithmforspeechseparation