Forward masking threshold estimation using neural networks and its application to parallel speech enhancement

Forward masking models have been used successfully in speech enhancement and audio coding. Presently, forward masking thresholds are estimated using simplified masking models which have been used for audio coding and speech enhancement applications. In this paper, an accurate approximation of forwar...

Full description

Bibliographic Details
Main Authors: Gunawan, Teddy Surya, Khalifa, Othman Omran, Ambikairajah, Eliathamby
Format: Article
Language:English
Published: IIUM Press 2010
Subjects:
Online Access:http://irep.iium.edu.my/2318/1/Forward_masking.pdf
_version_ 1825644297983098880
author Gunawan, Teddy Surya
Khalifa, Othman Omran
Ambikairajah, Eliathamby
author_facet Gunawan, Teddy Surya
Khalifa, Othman Omran
Ambikairajah, Eliathamby
author_sort Gunawan, Teddy Surya
collection IIUM
description Forward masking models have been used successfully in speech enhancement and audio coding. Presently, forward masking thresholds are estimated using simplified masking models which have been used for audio coding and speech enhancement applications. In this paper, an accurate approximation of forward masking threshold estimation using neural networks is proposed. A performance comparison to the other existing masking models in speech enhancement application is presented. Objective measures using PESQ demonstrates that our proposed forward masking model, provides significant improvements (5-15 %) over four existing models, when tested with speech signals corrupted by various noises at very low signal to noise ratios. Moreover, a parallel implementation of the speech enhancement algorithm was developed using Matlab parallel computing toolbox.
first_indexed 2024-03-05T22:30:48Z
format Article
id oai:generic.eprints.org:2318
institution International Islamic University Malaysia
language English
last_indexed 2024-03-05T22:30:48Z
publishDate 2010
publisher IIUM Press
record_format dspace
spelling oai:generic.eprints.org:23182017-06-13T03:58:28Z http://irep.iium.edu.my/2318/ Forward masking threshold estimation using neural networks and its application to parallel speech enhancement Gunawan, Teddy Surya Khalifa, Othman Omran Ambikairajah, Eliathamby TK Electrical engineering. Electronics Nuclear engineering Forward masking models have been used successfully in speech enhancement and audio coding. Presently, forward masking thresholds are estimated using simplified masking models which have been used for audio coding and speech enhancement applications. In this paper, an accurate approximation of forward masking threshold estimation using neural networks is proposed. A performance comparison to the other existing masking models in speech enhancement application is presented. Objective measures using PESQ demonstrates that our proposed forward masking model, provides significant improvements (5-15 %) over four existing models, when tested with speech signals corrupted by various noises at very low signal to noise ratios. Moreover, a parallel implementation of the speech enhancement algorithm was developed using Matlab parallel computing toolbox. IIUM Press 2010-07 Article PeerReviewed application/pdf en http://irep.iium.edu.my/2318/1/Forward_masking.pdf Gunawan, Teddy Surya and Khalifa, Othman Omran and Ambikairajah, Eliathamby (2010) Forward masking threshold estimation using neural networks and its application to parallel speech enhancement. IIUM Engineering Journal, 11 (1). pp. 15-26. ISSN 1511-788X http://www.iium.edu.my/ejournal/
spellingShingle TK Electrical engineering. Electronics Nuclear engineering
Gunawan, Teddy Surya
Khalifa, Othman Omran
Ambikairajah, Eliathamby
Forward masking threshold estimation using neural networks and its application to parallel speech enhancement
title Forward masking threshold estimation using neural networks and its application to parallel speech enhancement
title_full Forward masking threshold estimation using neural networks and its application to parallel speech enhancement
title_fullStr Forward masking threshold estimation using neural networks and its application to parallel speech enhancement
title_full_unstemmed Forward masking threshold estimation using neural networks and its application to parallel speech enhancement
title_short Forward masking threshold estimation using neural networks and its application to parallel speech enhancement
title_sort forward masking threshold estimation using neural networks and its application to parallel speech enhancement
topic TK Electrical engineering. Electronics Nuclear engineering
url http://irep.iium.edu.my/2318/1/Forward_masking.pdf
work_keys_str_mv AT gunawanteddysurya forwardmaskingthresholdestimationusingneuralnetworksanditsapplicationtoparallelspeechenhancement
AT khalifaothmanomran forwardmaskingthresholdestimationusingneuralnetworksanditsapplicationtoparallelspeechenhancement
AT ambikairajaheliathamby forwardmaskingthresholdestimationusingneuralnetworksanditsapplicationtoparallelspeechenhancement