Speech Separation Using Reduced Complexity DUET Algorithm in Real Environment

Speech Separation Using Reduced Complexity DUET Algorithm in Real Environment

The Degenerate Unmixing Estimation Technique (DUET) is a practical algorithm for source separation in anechoic environment. DUET performs source separation by frequency domain processing and is independent of the number of mixed sources. However performance of this algorithm for long speech signals...

Full description

Bibliographic Details
Main Authors: Farinaz Ackochekian, Mohsen Ashoreian
Format: Article
Language:English
Published: Najafabad Branch, Islamic Azad University 2012-07-01
Series:Journal of Intelligent Procedures in Electrical Technology
Subjects:
Blind Sources Separation
Mixed Speech Signal
Weighted histogram
Online Access:http://jipet.iaun.ac.ir/pdf_4269_f4c21e1e17fe2d7b61c05280dbf0a54e.html
id doaj-828986356989407bab245d0d39dbe9d6
record_format Article
spelling doaj-828986356989407bab245d0d39dbe9d62020-11-25T00:26:14ZengNajafabad Branch, Islamic Azad UniversityJournal of Intelligent Procedures in Electrical Technology2322-38712345-55942012-07-0131138Speech Separation Using Reduced Complexity DUET Algorithm in Real EnvironmentFarinaz Ackochekian0Mohsen Ashoreian1Najafabad Branch, Islamic Azad UniversityMajlesi Branch, Islamic Azad UniversityThe Degenerate Unmixing Estimation Technique (DUET) is a practical algorithm for source separation in anechoic environment. DUET performs source separation by frequency domain processing and is independent of the number of mixed sources. However performance of this algorithm for long speech signals is very slow. In this research we first down sampled real mixtures and then implemented the modified DUET algorithm. Using the proposed method reduces the implementation time almost one third of the basic algorithm.http://jipet.iaun.ac.ir/pdf_4269_f4c21e1e17fe2d7b61c05280dbf0a54e.htmlBlind Sources SeparationMixed Speech SignalWeighted histogram
collection DOAJ
language English
format Article
sources DOAJ
author Farinaz Ackochekian
Mohsen Ashoreian
spellingShingle Farinaz Ackochekian
Mohsen Ashoreian
Speech Separation Using Reduced Complexity DUET Algorithm in Real Environment
Journal of Intelligent Procedures in Electrical Technology
Blind Sources Separation
Mixed Speech Signal
Weighted histogram
author_facet Farinaz Ackochekian
Mohsen Ashoreian
author_sort Farinaz Ackochekian
title Speech Separation Using Reduced Complexity DUET Algorithm in Real Environment
title_short Speech Separation Using Reduced Complexity DUET Algorithm in Real Environment
title_full Speech Separation Using Reduced Complexity DUET Algorithm in Real Environment
title_fullStr Speech Separation Using Reduced Complexity DUET Algorithm in Real Environment
title_full_unstemmed Speech Separation Using Reduced Complexity DUET Algorithm in Real Environment
title_sort speech separation using reduced complexity duet algorithm in real environment
publisher Najafabad Branch, Islamic Azad University
series Journal of Intelligent Procedures in Electrical Technology
issn 2322-3871
2345-5594
publishDate 2012-07-01
description The Degenerate Unmixing Estimation Technique (DUET) is a practical algorithm for source separation in anechoic environment. DUET performs source separation by frequency domain processing and is independent of the number of mixed sources. However performance of this algorithm for long speech signals is very slow. In this research we first down sampled real mixtures and then implemented the modified DUET algorithm. Using the proposed method reduces the implementation time almost one third of the basic algorithm.
topic Blind Sources Separation
Mixed Speech Signal
Weighted histogram
url http://jipet.iaun.ac.ir/pdf_4269_f4c21e1e17fe2d7b61c05280dbf0a54e.html
work_keys_str_mv AT farinazackochekian speechseparationusingreducedcomplexityduetalgorithminrealenvironment
AT mohsenashoreian speechseparationusingreducedcomplexityduetalgorithminrealenvironment
_version_ 1725345234347360256

Similar Items