Show simple item record

dc.contributor.advisorSvendsen, Torbjørnnb_NO
dc.contributor.authorFjær, Bjørnar Gripnb_NO
dc.date.accessioned2014-12-19T13:46:37Z
dc.date.accessioned2015-12-22T11:45:11Z
dc.date.available2014-12-19T13:46:37Z
dc.date.available2015-12-22T11:45:11Z
dc.date.created2011-09-15nb_NO
dc.date.issued2011nb_NO
dc.identifier441345nb_NO
dc.identifier.urihttp://hdl.handle.net/11250/2370242
dc.description.abstractMost automatic speech recognition systems are based on statistical models thatrequire training. While these types of systems have reached recognition ratesthat are sufficient for many purposes, they perform poorly for speaker typesthat are not present in the training material. Children are often absent fromtraining material for speech recognizers, and creating good training materialfor children can be difficult and expensive.To address this issue, this thesis focuses on using adult training material totrain a recognizer for children by adapting the training material duringtraining. Instead of performing speaker-dependent adaptation duringrecognition, where computational power may be scarce, and responsiveness may beessential, adaptation is performed during training towards a class of speakers.Using a combination of vocal tract length normalization (VTLN) and cepstralmean normalization during training, promising results have been obtained. In aconnected-digits task, a reduction in errors as high as 70% was shown, with areduction of almost 50% in a large vocabulary task. Using VTLN to warp thesame training material several times, combining these warped materials to trainone recognizer, a similar reduction in errors was shown, but with an increasedrobustness indicating a less speaker-dependent system. It is also shown that apiecewise linear warping method is better suited to warp adult speech to childspeech, than a bilinear warping method.nb_NO
dc.languageengnb_NO
dc.publisherInstitutt for elektronikk og telekommunikasjonnb_NO
dc.subjectntnudaim:6125no_NO
dc.titleSpeech adaptation of special voice classesnb_NO
dc.typeMaster thesisnb_NO
dc.source.pagenumber67nb_NO
dc.contributor.departmentNorges teknisk-naturvitenskapelige universitet, Fakultet for informasjonsteknologi, matematikk og elektroteknikk, Institutt for elektronikk og telekommunikasjonnb_NO


Files in this item

Thumbnail
Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record