Application of Perceptual Filtering Models to Noisy Speech Signals Enhancement

This paper describes a new speech enhancement approach using perceptually based noise reduction. The proposed approach is based on the application of two perceptual filtering models to noisy speech signals: the gammatone and the gammachirp filter banks with nonlinear resolution according to the equi...

Full description

Saved in:
Bibliographic Details
Main Authors: Novlene Zoghlami, Zied Lachiri
Format: Article
Language:English
Published: Wiley 2012-01-01
Series:Journal of Electrical and Computer Engineering
Online Access:http://dx.doi.org/10.1155/2012/282019
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832567375940026368
author Novlene Zoghlami
Zied Lachiri
author_facet Novlene Zoghlami
Zied Lachiri
author_sort Novlene Zoghlami
collection DOAJ
description This paper describes a new speech enhancement approach using perceptually based noise reduction. The proposed approach is based on the application of two perceptual filtering models to noisy speech signals: the gammatone and the gammachirp filter banks with nonlinear resolution according to the equivalent rectangular bandwidth (ERB) scale. The perceptual filtering gives a number of subbands that are individually spectral weighted and modified according to two different noise suppression rules. The importance of an accurate noise estimate is related to the reduction of the musical noise artifacts in the processed speech that appears after classic subtractive process. In this context, we use continuous noise estimation algorithms. The performance of the proposed approach is evaluated on speech signals corrupted by real-world noises. Using objective tests based on the perceptual quality PESQ score and the quality rating of signal distortion (SIG), noise distortion (BAK) and overall quality (OVRL), and subjective test based on the quality rating of automatic speech recognition (ASR), we demonstrate that our speech enhancement approach using filter banks modeling the human auditory system outperforms the conventional spectral modification algorithms to improve quality and intelligibility of the enhanced speech signal.
format Article
id doaj-art-75f72552551d4586aef949d7897afc7a
institution Kabale University
issn 2090-0147
2090-0155
language English
publishDate 2012-01-01
publisher Wiley
record_format Article
series Journal of Electrical and Computer Engineering
spelling doaj-art-75f72552551d4586aef949d7897afc7a2025-02-03T01:01:40ZengWileyJournal of Electrical and Computer Engineering2090-01472090-01552012-01-01201210.1155/2012/282019282019Application of Perceptual Filtering Models to Noisy Speech Signals EnhancementNovlene Zoghlami0Zied Lachiri1LRSITI, Département Génie Electrique, Ecole Nationale des Ingénieurs de Tunis, BP 37, 1002 Le Belvédère, TunisiaLRSITI, Département Génie Electrique, Ecole Nationale des Ingénieurs de Tunis, BP 37, 1002 Le Belvédère, TunisiaThis paper describes a new speech enhancement approach using perceptually based noise reduction. The proposed approach is based on the application of two perceptual filtering models to noisy speech signals: the gammatone and the gammachirp filter banks with nonlinear resolution according to the equivalent rectangular bandwidth (ERB) scale. The perceptual filtering gives a number of subbands that are individually spectral weighted and modified according to two different noise suppression rules. The importance of an accurate noise estimate is related to the reduction of the musical noise artifacts in the processed speech that appears after classic subtractive process. In this context, we use continuous noise estimation algorithms. The performance of the proposed approach is evaluated on speech signals corrupted by real-world noises. Using objective tests based on the perceptual quality PESQ score and the quality rating of signal distortion (SIG), noise distortion (BAK) and overall quality (OVRL), and subjective test based on the quality rating of automatic speech recognition (ASR), we demonstrate that our speech enhancement approach using filter banks modeling the human auditory system outperforms the conventional spectral modification algorithms to improve quality and intelligibility of the enhanced speech signal.http://dx.doi.org/10.1155/2012/282019
spellingShingle Novlene Zoghlami
Zied Lachiri
Application of Perceptual Filtering Models to Noisy Speech Signals Enhancement
Journal of Electrical and Computer Engineering
title Application of Perceptual Filtering Models to Noisy Speech Signals Enhancement
title_full Application of Perceptual Filtering Models to Noisy Speech Signals Enhancement
title_fullStr Application of Perceptual Filtering Models to Noisy Speech Signals Enhancement
title_full_unstemmed Application of Perceptual Filtering Models to Noisy Speech Signals Enhancement
title_short Application of Perceptual Filtering Models to Noisy Speech Signals Enhancement
title_sort application of perceptual filtering models to noisy speech signals enhancement
url http://dx.doi.org/10.1155/2012/282019
work_keys_str_mv AT novlenezoghlami applicationofperceptualfilteringmodelstonoisyspeechsignalsenhancement
AT ziedlachiri applicationofperceptualfilteringmodelstonoisyspeechsignalsenhancement