Show simple item record

dc.contributor.authorCernocky, J.
dc.date.accessioned2016-05-03T10:52:16Z
dc.date.available2016-05-03T10:52:16Z
dc.date.issued1999-04cs
dc.identifier.citationRadioengineering. 1999, vol. 8, č. 1, s. 28-30. ISSN 1210-2512cs
dc.identifier.issn1210-2512
dc.identifier.urihttp://hdl.handle.net/11012/58258
dc.description.abstractCurrent systems for recognition, synthesis, very low bit-rate (VLBR) coding and text-independent speaker verification rely on sub-word units determined using phonetic knowledge. This paper presents an alternative to this approach - determination of speech units using AUSP (Automatic Language Independent Speech Processing) tools. Experimental results for speaker-dependent VLBR coding are reported on two databases: average rate of 120 bps for unit encoding was achieved. In verification, this approach was tested during 1998's NIST-NSA evaluation campaign with a MLP-based scoring system.en
dc.formattextcs
dc.format.extent28-30cs
dc.format.mimetypeapplication/pdfen
dc.language.isoencs
dc.publisherSpolečnost pro radioelektronické inženýrstvícs
dc.relation.ispartofRadioengineeringcs
dc.relation.urihttp://www.radioeng.cz/fulltexts/1999/99_01_07.pdfcs
dc.rightsCreative Commons Attribution 3.0 Unported Licenseen
dc.rights.urihttp://creativecommons.org/licenses/by/3.0/en
dc.subjectspeech processingen
dc.subjectspeaker verificationen
dc.subjectspeech codingen
dc.subjecttemporal decompositionen
dc.subjectmultigramsen
dc.subjecthidden Markov modelsen
dc.titleAutomatically Derived Units in the Speech Processingen
eprints.affiliatedInstitution.facultyFakulta eletrotechniky a komunikačních technologiícs
dc.coverage.issue1cs
dc.coverage.volume8cs
dc.rights.accessopenAccessen
dc.type.driverarticleen
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Creative Commons Attribution 3.0 Unported License
Except where otherwise noted, this item's license is described as Creative Commons Attribution 3.0 Unported License