356 0

Full metadata record

DC FieldValueLanguage
dc.contributor.author장준혁-
dc.date.accessioned2016-05-27T02:01:03Z-
dc.date.available2016-05-27T02:01:03Z-
dc.date.issued2015-01-
dc.identifier.citationAPPLIED ACOUSTICS, v. 87, Page. 205-211en_US
dc.identifier.issn0003-682X-
dc.identifier.urihttp://hdl.handle.net/20.500.11754/21392-
dc.identifier.urihttps://www.sciencedirect.com/science/article/pii/S0003682X14001686?via%3Dihub-
dc.description.abstractWe propose a novel approach to improve the performance of speech enhancement systems by using multiple linear regression to improve the technique of estimating the speech presence uncertainty. Conventional speech enhancement techniques use a fixed ratio Q of the a priori probability of speech presence and speech absence, or determine the value of Q simply by comparing one particular parameter against a threshold in deriving the speech absence probability (SAP) associated with the speech presence uncertainty. To further improve the performance of the SAP, we attempt to adaptively change Q according to a linear model consisting of the regression coefficients obtained by results from multiple linear regression analysis and two principal parameters: a priori SNR and the ratio between the local energy of the noisy speech and its derived minimum since these parameters correlate strongly with the value of Q. Distinct values of Q for each frequency in each frame are consequently assigned in time which leads to improved tracking performance of speech absence uncertainty and thus better performance of the proposed speech enhancement compared to conventional approaches. The superiority of the proposed approach is confirmed through extensive objective and subjective evaluations under various noise conditions. (C) 2014 Elsevier Ltd. All rights reserved.en_US
dc.description.urihttp://www.sciencedirect.com/science/article/pii/S0003682X14001686-
dc.language.isoenen_US
dc.publisherELSEVIER SCI LTDen_US
dc.relation.urihttp://www.sciencedirect.com/science/article/pii/S0003682X14001686-
dc.subjectA priori SNRen_US
dc.subjectSpeech absence probabilityen_US
dc.subjectMultiple linear regression analysisen_US
dc.titleEstimation of speech absence uncertainty based on multiple linear regression analysis for speech enhancementen_US
dc.typeArticleen_US
dc.relation.volume87-
dc.identifier.doi10.1016/j.apacoust.2014.06.017-
dc.relation.page205-211-
dc.relation.journalAPPLIED ACOUSTICS-
dc.contributor.googleauthorPark, Jihwan-
dc.contributor.googleauthorKim, Jong-Woong-
dc.contributor.googleauthorChang, Joon-Hyuk-
dc.contributor.googleauthorJin, Yu Gwang-
dc.contributor.googleauthorKim, Nam Soo-
dc.relation.code2015010561-
dc.sector.campusS-
dc.sector.daehakCOLLEGE OF ENGINEERING[S]-
dc.sector.departmentDEPARTMENT OF ELECTRONIC ENGINEERING-
dc.identifier.pidjchang-
Appears in Collections:
COLLEGE OF ENGINEERING[S](공과대학) > ELECTRONIC ENGINEERING(융합전자공학부) > Articles
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML


qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE