Publication:
Artificial bandwidth extension of spectral envelope with temporal clustering

dc.contributor.departmentDepartment of Computer Engineering
dc.contributor.departmentGraduate School of Sciences and Engineering
dc.contributor.kuauthorErzin, Engin
dc.contributor.kuauthorYağlı, Can
dc.contributor.kuprofileFaculty Member
dc.contributor.kuprofileMaster Student
dc.contributor.schoolcollegeinstituteCollege of Engineering
dc.contributor.schoolcollegeinstituteGRADUATE SCHOOL OF SCIENCES AND ENGINEERING
dc.contributor.yokid34503
dc.contributor.yokidN/A
dc.date.accessioned2024-11-09T23:35:25Z
dc.date.issued2011
dc.description.abstractWe present a new wideband spectral envelope estimation framework for the artificial bandwidth extension problem. The proposed framework builds temporal clusters of the joint sub-phone patterns of the narrowband and wideband speech signals using a parallel branch HMM structure. The joint sub-phone patterns define temporally correlated neighborhoods, in which a linear prediction filter estimates spectral features of the corresponding wideband signal from the narrowband signal. The proposed framework is compared to a benchmark vector quantization based artificial bandwidth extension algorithm. Performance evaluations are performed with three distinct objective metrics and a subjective A/B test. © 2011 IEEE.
dc.description.indexedbyScopus
dc.description.indexedbyWoS
dc.description.openaccessYES
dc.description.publisherscopeInternational
dc.description.sponsorshipInst. Electr. Electron. Eng. Signal Process. Soc.
dc.identifier.doi10.1109/ICASSP.2011.5947503
dc.identifier.isbn9781-4577-0539-7
dc.identifier.issn1520-6149
dc.identifier.linkhttps://www.scopus.com/inward/record.uri?eid=2-s2.0-80051617282anddoi=10.1109%2fICASSP.2011.5947503andpartnerID=40andmd5=3f8cf3d2f10c87e57039a47ecb1ba51f
dc.identifier.quartileN/A
dc.identifier.scopus2-s2.0-80051617282
dc.identifier.urihttp://dx.doi.org/10.1109/ICASSP.2011.5947503
dc.identifier.urihttps://hdl.handle.net/20.500.14288/12499
dc.identifier.wos296062405176
dc.keywordsLinear prediction
dc.keywordsLinear prediction filter
dc.keywordsNarrow bands
dc.keywordsNarrowband signal
dc.keywordsObjective metrics
dc.keywordsPerformance evaluation
dc.keywordsSpectral envelopes
dc.keywordsSpectral feature
dc.keywordsTemporal clustering
dc.keywordsWide-band
dc.keywordsWideband signals
dc.keywordsWideband speech
dc.keywordsBandwidth
dc.keywordsSignal processing
dc.keywordsTelephone sets
dc.keywordsVector quantization
dc.keywordsSpeech communication
dc.languageEnglish
dc.publisherIEEE
dc.sourceICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
dc.subjectComputer engineering
dc.titleArtificial bandwidth extension of spectral envelope with temporal clustering
dc.typeConference proceeding
dspace.entity.typePublication
local.contributor.authorid0000-0002-2715-2368
local.contributor.authoridN/A
local.contributor.kuauthorErzin, Engin
local.contributor.kuauthorYağlı, Can
local.publication.orgunit1College of Engineering
local.publication.orgunit1GRADUATE SCHOOL OF SCIENCES AND ENGINEERING
local.publication.orgunit2Department of Computer Engineering
local.publication.orgunit2Graduate School of Sciences and Engineering
relation.isOrgUnitOfPublication89352e43-bf09-4ef4-82f6-6f9d0174ebae
relation.isOrgUnitOfPublication3fc31c89-e803-4eb1-af6b-6258bc42c3d8
relation.isOrgUnitOfPublication.latestForDiscovery89352e43-bf09-4ef4-82f6-6f9d0174ebae
relation.isParentOrgUnitOfPublication8e756b23-2d4a-4ce8-b1b3-62c794a8c164
relation.isParentOrgUnitOfPublication434c9663-2b11-4e66-9399-c863e2ebae43
relation.isParentOrgUnitOfPublication.latestForDiscovery8e756b23-2d4a-4ce8-b1b3-62c794a8c164

Files