239 0

Full metadata record

DC FieldValueLanguage
dc.contributor.author장준혁-
dc.date.accessioned2021-11-30T01:18:09Z-
dc.date.available2021-11-30T01:18:09Z-
dc.date.issued2020-05-
dc.identifier.citationDIGITAL SIGNAL PROCESSING, v. 102, article no. 102760en_US
dc.identifier.issn1051-2004-
dc.identifier.issn1095-4333-
dc.identifier.urihttps://www.sciencedirect.com/science/article/pii/S1051200420301056?via%3Dihub-
dc.identifier.urihttps://repository.hanyang.ac.kr/handle/20.500.11754/166516-
dc.description.abstractIn this paper, we propose a deep neural network (DNN) ensemble for reducing artificial noise in speech bandwidth extension (BWE). The proposed DNN ensemble consists of three DNN models; one is a classification model, and the other two are regression models. When estimating sub-band energies of the high-frequency region using sequential DNNs in a frequency domain, the over-estimation of sub-band energies causes annoying artificial noise. To mitigate this artificial noise, we design a DNN classification model that can classify over-estimation frames against normal frames. Then, we separately develop two DNN regression models using half of the entire training set and a limited training set built with overestimation frames and some normal frames to improve the performance at the over-estimation frames. Since the outputs of the classification model are probabilities of either a normal frame or an overestimation frame, respectively, two regression models are adjustably combined by using the probabilistic weights; thus, the final output of the DNN ensemble is the weighted sum of two estimated sub-band energies. As a result, artificial noise is significantly reduced, yielding improved speech quality. The proposed method is objectively and subjectively evaluated by comparing it with conventional approaches.en_US
dc.description.sponsorshipThis work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIP) (No. 2017R1A2A1A17069651).en_US
dc.language.isoenen_US
dc.publisherACADEMIC PRESS INC ELSEVIER SCIENCEen_US
dc.subjectBandwidth extensionen_US
dc.subjectDeep neural networken_US
dc.subjectEnsembleen_US
dc.subjectArtificial noiseen_US
dc.titleDeep neural network ensemble for reducing artificial noise in bandwidth extensionen_US
dc.typeArticleen_US
dc.relation.volume102-
dc.identifier.doi10.1016/j.dsp.2020.102760-
dc.relation.page1-6-
dc.relation.journalDIGITAL SIGNAL PROCESSING-
dc.contributor.googleauthorNoh, Kyoungjin-
dc.contributor.googleauthorChang, Joon-Hyuk-
dc.relation.code2020049761-
dc.sector.campusS-
dc.sector.daehakCOLLEGE OF ENGINEERING[S]-
dc.sector.departmentSCHOOL 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