Convex combination framework for a priori SNR estimation in speech enhancement

© 2017 IEEE. The paper proposes a convex combination fusion function based on a sigmoid function for the estimation of the a priori SNR in a speech enhancement framework with critical frequency band processing. The proposed method does not only eliminate the one frame delay generated by the well-kno...

Full description

Bibliographic Details
Main Authors: Nahma, L., Yong, P., Dam, Hai Huyen Heidi, Nordholm, Sven
Format: Conference Paper
Published: 2017
Online Access:http://hdl.handle.net/20.500.11937/55889
_version_ 1848759733494743040
author Nahma, L.
Yong, P.
Dam, Hai Huyen Heidi
Nordholm, Sven
author_facet Nahma, L.
Yong, P.
Dam, Hai Huyen Heidi
Nordholm, Sven
author_sort Nahma, L.
building Curtin Institutional Repository
collection Online Access
description © 2017 IEEE. The paper proposes a convex combination fusion function based on a sigmoid function for the estimation of the a priori SNR in a speech enhancement framework with critical frequency band processing. The proposed method does not only eliminate the one frame delay generated by the well-known decision directed approach but also increases the adaptation speed during abrupt changes in the SNR estimation. As a result, the advantage of low musical noise has been maintained while more weak speech components have been preserved. Experimental results using instrumental and subjective measures also indicate improvement in speech quality compared to the reference methods.
first_indexed 2025-11-14T10:04:34Z
format Conference Paper
id curtin-20.500.11937-55889
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T10:04:34Z
publishDate 2017
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-558892017-09-13T16:11:02Z Convex combination framework for a priori SNR estimation in speech enhancement Nahma, L. Yong, P. Dam, Hai Huyen Heidi Nordholm, Sven © 2017 IEEE. The paper proposes a convex combination fusion function based on a sigmoid function for the estimation of the a priori SNR in a speech enhancement framework with critical frequency band processing. The proposed method does not only eliminate the one frame delay generated by the well-known decision directed approach but also increases the adaptation speed during abrupt changes in the SNR estimation. As a result, the advantage of low musical noise has been maintained while more weak speech components have been preserved. Experimental results using instrumental and subjective measures also indicate improvement in speech quality compared to the reference methods. 2017 Conference Paper http://hdl.handle.net/20.500.11937/55889 10.1109/ICASSP.2017.7953103 restricted
spellingShingle Nahma, L.
Yong, P.
Dam, Hai Huyen Heidi
Nordholm, Sven
Convex combination framework for a priori SNR estimation in speech enhancement
title Convex combination framework for a priori SNR estimation in speech enhancement
title_full Convex combination framework for a priori SNR estimation in speech enhancement
title_fullStr Convex combination framework for a priori SNR estimation in speech enhancement
title_full_unstemmed Convex combination framework for a priori SNR estimation in speech enhancement
title_short Convex combination framework for a priori SNR estimation in speech enhancement
title_sort convex combination framework for a priori snr estimation in speech enhancement
url http://hdl.handle.net/20.500.11937/55889