Investigating Explicit Model Transformations for Speaker Normalization
2008 (English)In: Proceedings of ISCA ITRW Speech Analysis and Processing for Knowledge Discovery / [ed] Paul Dalsgaard, Christian Fischer Pedersen, Ove Andersen, Aalborg, Denmark: ISCA/AAU , 2008Conference paper (Refereed)
In this work we extend the test utterance adaptation techniqueused in vocal tract length normalization to a larger number ofspeaker characteristic features. We perform partially joint estimation of four features: the VTLN warping factor, the corner position of the piece-wise linear warping function, spectral tilt in voiced segments, and model variance scaling. In experiments on the Swedish PF-Star children database, joint estimation of warping factor and variance scaling lowered the recognition error rate compared to warping factor alone.
Place, publisher, year, edition, pages
Aalborg, Denmark: ISCA/AAU , 2008.
speaker normalization, adaptation, VTLN
Computer Science Language Technology (Computational Linguistics)
IdentifiersURN: urn:nbn:se:kth:diva-51962ISBN: 978-87-92328-00-7OAI: oai:DiVA.org:kth-51962DiVA: diva2:465252
ISCA ITRW Speech Analysis and Processing for Knowledge Discovery
tmh_import_11_12_14. QC 201201122011-12-142011-12-142012-01-12Bibliographically approved