Change search
ReferencesLink to record
Permanent link

Direct link
Speech adaptation of special voice classes
Norwegian University of Science and Technology, Faculty of Information Technology, Mathematics and Electrical Engineering, Department of Electronics and Telecommunications.
2011 (English)MasteroppgaveStudent thesis
Abstract [en]

Most automatic speech recognition systems are based on statistical models that require training. While these types of systems have reached recognition rates that are sufficient for many purposes, they perform poorly for speaker types that are not present in the training material. Children are often absent from training material for speech recognizers, and creating good training material for children can be difficult and expensive. To address this issue, this thesis focuses on using adult training material to train a recognizer for children by adapting the training material during training. Instead of performing speaker-dependent adaptation during recognition, where computational power may be scarce, and responsiveness may be essential, adaptation is performed during training towards a class of speakers. Using a combination of vocal tract length normalization (VTLN) and cepstral mean normalization during training, promising results have been obtained. In a connected-digits task, a reduction in errors as high as 70% was shown, with a reduction of almost 50% in a large vocabulary task. Using VTLN to warp the same training material several times, combining these warped materials to train one recognizer, a similar reduction in errors was shown, but with an increased robustness indicating a less speaker-dependent system. It is also shown that a piecewise linear warping method is better suited to warp adult speech to child speech, than a bilinear warping method.

Place, publisher, year, edition, pages
Institutt for elektronikk og telekommunikasjon , 2011. , 67 p.
Keyword [no]
ntnudaim:6125, MTEL elektronikk, Akustikk
URN: urn:nbn:no:ntnu:diva-13646Local ID: ntnudaim:6125OAI: diva2:441345
Available from: 2011-09-15 Created: 2011-09-15

Open Access in DiVA

fulltext(781 kB)211 downloads
File information
File name FULLTEXT01.pdfFile size 781 kBChecksum SHA-512
Type fulltextMimetype application/pdf
cover(47 kB)24 downloads
File information
File name COVER01.pdfFile size 47 kBChecksum SHA-512
Type coverMimetype application/pdf
attachment(22 kB)30 downloads
File information
File name ATTACHMENT01.zipFile size 22 kBChecksum SHA-512
Type attachmentMimetype application/zip

By organisation
Department of Electronics and Telecommunications

Search outside of DiVA

GoogleGoogle Scholar
Total: 211 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 71 hits
ReferencesLink to record
Permanent link

Direct link