Evaluation of source separation using projection pursuit algorithm for computer-based auditory training system

Abrar Hussain, Kalaivani Chell, Siti Zamratol Mai Sarah Mukari

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Difficulty of understanding speech in noise among the elderly community necessitates the need for Auditory Training which has made a renewal of interest in the last decade with the auditory training applications. This interest is perhaps spurred by advances in computer-based technology. In computer-based training, speech signals are considered as training stimuli where input speech signals need to be verified prior to training as the speech signals are mixed with noise signals in real-life acoustic environment. Computer-based Auditory Training System can be embedded with input speech verifying module. Input speech verifying module is employed with speech and noise separator simulator. This simulator needs to guarantee accurate separation of speech from noise signals. Therefore, in this research, Projection Pursuit (PP) algorithm under Blind Source Separation (BSS) method is intended to separate the speech source signals which are mixed with speech babble. This article uses Malay language based sentences which differ in word length and hence number of sample values. The experimental simulation considers two-channel random and linear mixing of speech sources and speech babble as noise signal. The aim of this study is to evaluate the performance of the anticipated PP algorithm for various sample values of speech signals which varies in time duration due to word length dissimilarity. Simulation results show that PP algorithm is feasible for source separation. As a consequence, high correlation value of r ≥ 0.99 is obtained between extracted speech signal and original speech signal for all categories of speech signals. It is further verified by the maximum nongaussianity of extracted speech signal which has high kurtosis value of 32.

Original languageEnglish
Title of host publication2017 7th IEEE International Conference on System Engineering and Technology, ICSET 2017 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages145-150
Number of pages6
ISBN (Electronic)9781538603833
DOIs
Publication statusPublished - 27 Nov 2017
Event7th IEEE International Conference on System Engineering and Technology, ICSET 2017 - Shah Alam, Malaysia
Duration: 2 Oct 20173 Oct 2017

Other

Other7th IEEE International Conference on System Engineering and Technology, ICSET 2017
CountryMalaysia
CityShah Alam
Period2/10/173/10/17

Fingerprint

Projection Pursuit
Source separation
Source Separation
Speech Signal
Evaluation
Simulator
Training
Speech
Module
Blind Source Separation
Separator
Kurtosis
Renewal
Dissimilarity
Acoustics
Simulation
Simulators
Vary
Blind source separation

Keywords

  • auditory training
  • blind source separation
  • pursuit algorithms
  • source separation

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Control and Optimization
  • Computer Networks and Communications
  • Human-Computer Interaction

Cite this

Hussain, A., Chell, K., & Mukari, S. Z. M. S. (2017). Evaluation of source separation using projection pursuit algorithm for computer-based auditory training system. In 2017 7th IEEE International Conference on System Engineering and Technology, ICSET 2017 - Proceedings (pp. 145-150). [8123436] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICSEngT.2017.8123436

Evaluation of source separation using projection pursuit algorithm for computer-based auditory training system. / Hussain, Abrar; Chell, Kalaivani; Mukari, Siti Zamratol Mai Sarah.

2017 7th IEEE International Conference on System Engineering and Technology, ICSET 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. p. 145-150 8123436.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Hussain, A, Chell, K & Mukari, SZMS 2017, Evaluation of source separation using projection pursuit algorithm for computer-based auditory training system. in 2017 7th IEEE International Conference on System Engineering and Technology, ICSET 2017 - Proceedings., 8123436, Institute of Electrical and Electronics Engineers Inc., pp. 145-150, 7th IEEE International Conference on System Engineering and Technology, ICSET 2017, Shah Alam, Malaysia, 2/10/17. https://doi.org/10.1109/ICSEngT.2017.8123436
Hussain A, Chell K, Mukari SZMS. Evaluation of source separation using projection pursuit algorithm for computer-based auditory training system. In 2017 7th IEEE International Conference on System Engineering and Technology, ICSET 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2017. p. 145-150. 8123436 https://doi.org/10.1109/ICSEngT.2017.8123436
Hussain, Abrar ; Chell, Kalaivani ; Mukari, Siti Zamratol Mai Sarah. / Evaluation of source separation using projection pursuit algorithm for computer-based auditory training system. 2017 7th IEEE International Conference on System Engineering and Technology, ICSET 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 145-150
@inproceedings{c5a79d998763429986c42ff2e0e26a3c,
title = "Evaluation of source separation using projection pursuit algorithm for computer-based auditory training system",
abstract = "Difficulty of understanding speech in noise among the elderly community necessitates the need for Auditory Training which has made a renewal of interest in the last decade with the auditory training applications. This interest is perhaps spurred by advances in computer-based technology. In computer-based training, speech signals are considered as training stimuli where input speech signals need to be verified prior to training as the speech signals are mixed with noise signals in real-life acoustic environment. Computer-based Auditory Training System can be embedded with input speech verifying module. Input speech verifying module is employed with speech and noise separator simulator. This simulator needs to guarantee accurate separation of speech from noise signals. Therefore, in this research, Projection Pursuit (PP) algorithm under Blind Source Separation (BSS) method is intended to separate the speech source signals which are mixed with speech babble. This article uses Malay language based sentences which differ in word length and hence number of sample values. The experimental simulation considers two-channel random and linear mixing of speech sources and speech babble as noise signal. The aim of this study is to evaluate the performance of the anticipated PP algorithm for various sample values of speech signals which varies in time duration due to word length dissimilarity. Simulation results show that PP algorithm is feasible for source separation. As a consequence, high correlation value of r ≥ 0.99 is obtained between extracted speech signal and original speech signal for all categories of speech signals. It is further verified by the maximum nongaussianity of extracted speech signal which has high kurtosis value of 32.",
keywords = "auditory training, blind source separation, pursuit algorithms, source separation",
author = "Abrar Hussain and Kalaivani Chell and Mukari, {Siti Zamratol Mai Sarah}",
year = "2017",
month = "11",
day = "27",
doi = "10.1109/ICSEngT.2017.8123436",
language = "English",
pages = "145--150",
booktitle = "2017 7th IEEE International Conference on System Engineering and Technology, ICSET 2017 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Evaluation of source separation using projection pursuit algorithm for computer-based auditory training system

AU - Hussain, Abrar

AU - Chell, Kalaivani

AU - Mukari, Siti Zamratol Mai Sarah

PY - 2017/11/27

Y1 - 2017/11/27

N2 - Difficulty of understanding speech in noise among the elderly community necessitates the need for Auditory Training which has made a renewal of interest in the last decade with the auditory training applications. This interest is perhaps spurred by advances in computer-based technology. In computer-based training, speech signals are considered as training stimuli where input speech signals need to be verified prior to training as the speech signals are mixed with noise signals in real-life acoustic environment. Computer-based Auditory Training System can be embedded with input speech verifying module. Input speech verifying module is employed with speech and noise separator simulator. This simulator needs to guarantee accurate separation of speech from noise signals. Therefore, in this research, Projection Pursuit (PP) algorithm under Blind Source Separation (BSS) method is intended to separate the speech source signals which are mixed with speech babble. This article uses Malay language based sentences which differ in word length and hence number of sample values. The experimental simulation considers two-channel random and linear mixing of speech sources and speech babble as noise signal. The aim of this study is to evaluate the performance of the anticipated PP algorithm for various sample values of speech signals which varies in time duration due to word length dissimilarity. Simulation results show that PP algorithm is feasible for source separation. As a consequence, high correlation value of r ≥ 0.99 is obtained between extracted speech signal and original speech signal for all categories of speech signals. It is further verified by the maximum nongaussianity of extracted speech signal which has high kurtosis value of 32.

AB - Difficulty of understanding speech in noise among the elderly community necessitates the need for Auditory Training which has made a renewal of interest in the last decade with the auditory training applications. This interest is perhaps spurred by advances in computer-based technology. In computer-based training, speech signals are considered as training stimuli where input speech signals need to be verified prior to training as the speech signals are mixed with noise signals in real-life acoustic environment. Computer-based Auditory Training System can be embedded with input speech verifying module. Input speech verifying module is employed with speech and noise separator simulator. This simulator needs to guarantee accurate separation of speech from noise signals. Therefore, in this research, Projection Pursuit (PP) algorithm under Blind Source Separation (BSS) method is intended to separate the speech source signals which are mixed with speech babble. This article uses Malay language based sentences which differ in word length and hence number of sample values. The experimental simulation considers two-channel random and linear mixing of speech sources and speech babble as noise signal. The aim of this study is to evaluate the performance of the anticipated PP algorithm for various sample values of speech signals which varies in time duration due to word length dissimilarity. Simulation results show that PP algorithm is feasible for source separation. As a consequence, high correlation value of r ≥ 0.99 is obtained between extracted speech signal and original speech signal for all categories of speech signals. It is further verified by the maximum nongaussianity of extracted speech signal which has high kurtosis value of 32.

KW - auditory training

KW - blind source separation

KW - pursuit algorithms

KW - source separation

UR - http://www.scopus.com/inward/record.url?scp=85041398738&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85041398738&partnerID=8YFLogxK

U2 - 10.1109/ICSEngT.2017.8123436

DO - 10.1109/ICSEngT.2017.8123436

M3 - Conference contribution

AN - SCOPUS:85041398738

SP - 145

EP - 150

BT - 2017 7th IEEE International Conference on System Engineering and Technology, ICSET 2017 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -