265 0

Full metadata record

DC FieldValueLanguage
dc.contributor.author이수정-
dc.date.accessioned2019-03-19T05:55:22Z-
dc.date.available2019-03-19T05:55:22Z-
dc.date.issued2016-11-
dc.identifier.citationMULTIMEDIA TOOLS AND APPLICATIONS, v. 76, no. 23, Page. 24917–24929en_US
dc.identifier.issn1380-7501-
dc.identifier.issn1573-7721-
dc.identifier.urihttps://link.springer.com/article/10.1007%2Fs11042-016-4122-7-
dc.identifier.urihttps://repository.hanyang.ac.kr/handle/20.500.11754/100986-
dc.description.abstractIn this paper, we propose a statistical model-based speech enhancement technique using the spectral difference scheme for the speech recognition in virtual reality. In the analyzing step, two principal parameters, the weighting parameter in the decision-directed (DD) method and the long-term smoothing parameter in noise estimation, are uniquely determined as optimal operating points according to the spectral difference under various noise conditions. These optimal operating points, which are specific according to different spectral differences, are estimated based on the composite measure, which is a relevant criterion in terms of speech quality. An efficient mapping function is also presented to provide an index of the metric table associated with the spectral difference so that operating points can be determined according to various noise conditions for an on-line step. In the on-line speech enhancement step, different parameters are chosen on a frame-by-frame basis under the metric table of the spectral difference. The performance of the proposed method is evaluated using objective and subjective speech quality measures in various noise environments. Our experimental results show that the proposed algorithm yields better performances than conventional algorithms.en_US
dc.description.sponsorshipThis work was also supported by National Research Foundation (NRF) of Korea grant funded by (2014R1A2A1A10049735)en_US
dc.language.isoenen_US
dc.publisherSPRINGERen_US
dc.subjectSpeech enhancementen_US
dc.subjectNoise reductionen_US
dc.subjectSpeech recognitionen_US
dc.subjectSpectral differenceen_US
dc.titleSpectral Difference for Statistical Model-Based Speech Enhancement in Speech Recognitionen_US
dc.typeArticleen_US
dc.identifier.doi10.1007/s11042-016-4122-7-
dc.relation.page1-13-
dc.relation.journalMULTIMEDIA TOOLS AND APPLICATIONS-
dc.contributor.googleauthorLee, Soojeong-
dc.contributor.googleauthorChang, Joon-Hyuk-
dc.relation.code2016007720-
dc.sector.campusS-
dc.sector.daehakINDUSTRY-UNIVERSITY COOPERATION FOUNDATION[S]-
dc.sector.departmentRESEARCH INSTITUTE-
dc.identifier.pidleesoo86-
Appears in Collections:
INDUSTRY-UNIVERSITY COOPERATION FOUNDATION[S](산학협력단) > ETC
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