Show simple item record

dc.contributor.authorWang, Yu
dc.contributor.authorZhang, C
dc.contributor.authorGales, Mark
dc.contributor.authorWoodland, PC
dc.date.accessioned2018-12-01T00:30:08Z
dc.date.available2018-12-01T00:30:08Z
dc.date.issued2018
dc.identifier.isbn978-1-5108-7221-9
dc.identifier.issn2308-457X
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/286180
dc.description.abstractSpeaker independent (SI) Tandem systems trained by joint optimisation of bottleneck (BN) deep neural networks (DNNs) and Gaussian mixture models (GMMs) have been found to produce similar word error rates (WERs) to Hybrid DNN systems. A key advantage of using GMMs is that existing speaker adaptation methods, such as maximum likelihood linear regression (MLLR), can be used which to account for diverse speaker variations and improve system robustness. This paper investigates speaker adaptation and adaptive training (SAT) schemes for jointly optimised Tandem systems. Adaptation techniques investigated include constrained MLLR (CMLLR) transforms based on BN features for SAT as well as MLLR and parameterised sigmoid functions for unsupervised test-time adaptation. Experiments using English multi-genre broadcast (MGB3) data show that CMLLR SAT yields a 4% relative WER reduction over jointly trained Tandem and Hybrid SI systems, and further reductions in WER are obtained by system combination.
dc.publisherISCA
dc.titleSpeaker adaptation and adaptive training for jointly optimised tandem systems
dc.typeConference Object
prism.endingPage876
prism.publicationDate2018
prism.publicationNameProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
prism.startingPage872
prism.volume2018-September
dc.identifier.doi10.17863/CAM.33492
rioxxterms.versionofrecord10.21437/Interspeech.2018-2432
rioxxterms.licenseref.urihttp://www.rioxx.net/licenses/all-rights-reserved
rioxxterms.licenseref.startdate2018-01-01
dc.contributor.orcidGales, Mark [0000-0002-5311-8219]
dc.identifier.eissn1990-9772
rioxxterms.typeConference Paper/Proceeding/Abstract
cam.issuedOnline2018-09-02
pubs.conference-nameInterspeech 2018
rioxxterms.freetoread.startdate2019-01-01


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record