Effects of intra-frame noise smoothing on speech enhancement algorithms

Authors:
Anis Ben Aicha;Sofia Ben Jebara
Affiliations:
Unité de recherche TECHTRA, Ecole Supérieure des Communications de Tunis, Université de Carthage, Ariana, Tunisie;Unité de recherche TECHTRA, Ecole Supérieure des Communications de Tunis, Université de Carthage, Ariana, Tunisie
Venue:
NOLISP'11 Proceedings of the 5th international conference on Advances in nonlinear speech processing
Year:
2011

Citing 5
Cited 0

Assessment for automatic speech recognition II: NOISEX-92: a database and an experiment to study the effect of additive noise on speech recognition systems

Speech Communication - Special issue on speech processing in adverse conditions
A geometric approach to spectral subtraction

Speech Communication
Noise Reduction in Speech Processing

Noise Reduction in Speech Processing
Quantitative perceptual separation of two kinds of degradation in speech denoising applications

NOLISP'07 Proceedings of the 2007 international conference on Advances in nonlinear speech processing
Evaluation of Objective Quality Measures for Speech Enhancement

IEEE Transactions on Audio, Speech, and Language Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Performances of speech enhancement algorithms depend greatly on the accuracy of the estimated noise. In this paper, we explain in details the relationship between noise estimation and denoised speech quality. Firstly, the effect of silence length on noise estimation is analyzed. We particularly show the importance of noise smoothing over frames on denoising quality. This study leads to the development of a new technique to smooth the estimated noise power spectrum over frequency bins of the same frame. Compared to inter-frame smoothing, experimental results show that this intra-frame smoothing has a good impact on the denoised speech. Quality is evaluated over three dimensions: speech distortion, residual background noise and overall quality.