Show simple item record

Two-pass decision tree construction for unsupervised adaptation of HMM-based synthesis models

dc.creatorGibson, Matthew
dc.date.accessioned2018-11-24T13:10:51Z
dc.date.available2010-08-26T13:34:34Z
dc.date.available2018-11-24T13:10:51Z
dc.date.issued2009
dc.identifierhttp://www.dspace.cam.ac.uk/handle/1810/226336
dc.identifier.urihttp://repository.aust.edu.ng/xmlui/handle/123456789/2835
dc.description.abstractHidden Markov model (HMM) -based speech synthesis systems possess several advantages over concatenative synthesis systems. One such advantage is the relative ease with which HMM-based systems are adapted to speakers not present in the training dataset. Speaker adaptation methods used in the field of HMM-based automatic speech recognition (ASR) are adopted for this task. In the case of unsupervised speaker adaptation, previous work has used a supplementary set of acoustic models to firstly estimate the transcription of the adaptation data. By defining a mapping between HMM-based synthesis models and ASR-style models, this paper introduces an approach to the unsupervised speaker adaptation task for HMM-based speech synthesis models which avoids the need for supplementary acoustic models. Further, this enables unsupervised adaptation of HMM-based speech synthesis models without the need to perform linguistic analysis of the estimated transcription of the adaptation data.
dc.subjectHMM-based speech synthesis
dc.subjectunsupervised speaker adaptation
dc.titleTwo-pass decision tree construction for unsupervised adaptation of HMM-based synthesis models
dc.typeArticle


Files in this item

FilesSizeFormatView
is2009-mgibson.pdf90.05Kbapplication/pdfView/Open

This item appears in the following Collection(s)

Show simple item record