Repository logo
 

Comparison of forced-alignment speech recognition and humans for generating reference VAD

Simple item page
dc.contributor.authorKraljevski, I.
dc.contributor.authorTan, Z-H
dc.contributor.authorBissiri, Maria Paola
dc.date.accessioned2018-06-29T15:51:44Z
dc.date.available2018-06-29T15:51:44Z
dc.date.issued2015
dc.description.abstractThis present paper aims to answer the question whether forced-alignment speech recognition can be used as an alternative to humans in generating reference Voice Activity Detection (VAD) transcriptions. An investigation of the level of agreement between automatic/manual VAD transcriptions and the reference ones produced by a human expert was carried out. Thereafter, statistical analysis was employed on the automatically produced and the collected manual transcriptions. Experimental results confirmed that forced-alignment speech recognition can provide accurate and consistent VAD labels.
dc.description.eprintid4422
dc.description.facultycasl
dc.description.ispublishedpub
dc.description.statuspub
dc.format.extent2937-2941
dc.identifierER4422
dc.identifier.citationKraljevski, I., Tan, Z. & Bissiri, M. (2015) Comparison of forced-alignment speech recognition and humans for generating reference VAD, Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, pp. 2937-2941.
dc.identifier.isbn1990-9770
dc.identifier.issn2308457X
dc.identifier.urihttps://eresearch.qmu.ac.uk/handle/20.500.12289/4422
dc.publisherInternational Speech and Communication Association
dc.relation.ispartofProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
dc.relation.ispartofINTERSPEECH-2015 - Proceedings of Interspeech 2015, September 2015, Dresden, Germany
dc.titleComparison of forced-alignment speech recognition and humans for generating reference VAD
dc.typearticle
dcterms.accessRightspublic
qmu.authorBissiri, Maria Paola
qmu.centreCASL
qmu.centreCASLen
refterms.dateFCA2016-08-16
refterms.dateFCD2016-08-15
rioxxterms.typearticle

Files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
4422.pdf
Size:
242.1 KB
Format:
Adobe Portable Document Format
Download

Collections

CASL