The development of a forward masking model using neural networks and its application to speech enhancement

Gunawan, Teddy Surya and Khalifa, Othman Omran and Ambikairajah, Eliathamby (2008) The development of a forward masking model using neural networks and its application to speech enhancement. In: International Conference on Computer and Communication Engineering (ICCCE 2008), 13 -15 May 2008 , Kuala Lumpur, Malaysia.

PDF (The Development of a Forward Masking Model using Neural Networks and Its Application to Speech Enhancement ) - Published Version Restricted to Registered users only Download (351kB) | Request a copy

Abstract

Forward masking models have been used successfully in speech enhancement and audio coding. Currently, simple forward masking models have been employed to predict the forward masking threshold. In this paper, an accurate approximation of forward masking threshold 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.

Item Type:	Conference or Workshop Item (Full Paper)
Additional Information:	5588/2338
Subjects:	T Technology > TK Electrical engineering. Electronics Nuclear engineering
Kulliyyahs/Centres/Divisions/Institutes (Can select more than one option. Press CONTROL button):	Kulliyyah of Engineering > Department of Electrical and Computer Engineering
Depositing User:	Prof. Dr. Teddy Surya Gunawan
Date Deposited:	08 Aug 2012 15:17
Last Modified:	08 Aug 2012 15:17
URI:	http://irep.iium.edu.my/id/eprint/2338

Actions (login required)

View Item