Optimizaton and evaluation of sigmoid function with a priori SNR estimate for real-time speech enhancement

In this paper, an a priori signal-to-noise ratio (SNR) estimator with a modified sigmoid gain function is proposed for real-time speech enhancement. The proposed sigmoid gain function has three parameters, which can be optimized such that they match conventional gain functions. In addition, the join...

Full description

Bibliographic Details
Main Authors: Yong, Pei, Nordholm, Sven, Dam, Hai
Format: Journal Article
Published: Elsevier 2013
Subjects:
Online Access:http://hdl.handle.net/20.500.11937/34679
_version_ 1848754288830971904
author Yong, Pei
Nordholm, Sven
Dam, Hai
author_facet Yong, Pei
Nordholm, Sven
Dam, Hai
author_sort Yong, Pei
building Curtin Institutional Repository
collection Online Access
description In this paper, an a priori signal-to-noise ratio (SNR) estimator with a modified sigmoid gain function is proposed for real-time speech enhancement. The proposed sigmoid gain function has three parameters, which can be optimized such that they match conventional gain functions. In addition, the joint temporal dynamics between the SNR estimate and the spectral gain function is investigated to improve the performance of the speech enhancement scheme. As the widely-used decision-directed (DD) a priori SNR estimate has a well-known one-frame delay that leads to the degradation of speech quality, a modified a priori SNR estimator is proposed for the DD approach to overcome this delay. Evaluations are performed by utilizing the objective evaluation metric that measures the trade-off between the noise reduction, the speech distortion and the musical noise in the enhanced signal. The results are compared using the PESQ and the SNRseg measures as well as subjective listening tests. Simulation results show that the proposed gain function, which can flexibly model exponential distributions, is a potential alternative speech enhancement gain function.
first_indexed 2025-11-14T08:38:02Z
format Journal Article
id curtin-20.500.11937-34679
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T08:38:02Z
publishDate 2013
publisher Elsevier
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-346792017-09-13T15:24:47Z Optimizaton and evaluation of sigmoid function with a priori SNR estimate for real-time speech enhancement Yong, Pei Nordholm, Sven Dam, Hai Speech enhancement Sigmoid function Decision-directed approach SNR estimation Objective evaluation In this paper, an a priori signal-to-noise ratio (SNR) estimator with a modified sigmoid gain function is proposed for real-time speech enhancement. The proposed sigmoid gain function has three parameters, which can be optimized such that they match conventional gain functions. In addition, the joint temporal dynamics between the SNR estimate and the spectral gain function is investigated to improve the performance of the speech enhancement scheme. As the widely-used decision-directed (DD) a priori SNR estimate has a well-known one-frame delay that leads to the degradation of speech quality, a modified a priori SNR estimator is proposed for the DD approach to overcome this delay. Evaluations are performed by utilizing the objective evaluation metric that measures the trade-off between the noise reduction, the speech distortion and the musical noise in the enhanced signal. The results are compared using the PESQ and the SNRseg measures as well as subjective listening tests. Simulation results show that the proposed gain function, which can flexibly model exponential distributions, is a potential alternative speech enhancement gain function. 2013 Journal Article http://hdl.handle.net/20.500.11937/34679 10.1016/j.specom.2012.09.004 Elsevier restricted
spellingShingle Speech enhancement
Sigmoid function
Decision-directed approach
SNR estimation
Objective evaluation
Yong, Pei
Nordholm, Sven
Dam, Hai
Optimizaton and evaluation of sigmoid function with a priori SNR estimate for real-time speech enhancement
title Optimizaton and evaluation of sigmoid function with a priori SNR estimate for real-time speech enhancement
title_full Optimizaton and evaluation of sigmoid function with a priori SNR estimate for real-time speech enhancement
title_fullStr Optimizaton and evaluation of sigmoid function with a priori SNR estimate for real-time speech enhancement
title_full_unstemmed Optimizaton and evaluation of sigmoid function with a priori SNR estimate for real-time speech enhancement
title_short Optimizaton and evaluation of sigmoid function with a priori SNR estimate for real-time speech enhancement
title_sort optimizaton and evaluation of sigmoid function with a priori snr estimate for real-time speech enhancement
topic Speech enhancement
Sigmoid function
Decision-directed approach
SNR estimation
Objective evaluation
url http://hdl.handle.net/20.500.11937/34679