Show simple item record

dc.contributor.authorGibson, Matthew
dc.date.accessioned2010-08-26T13:34:34Z
dc.date.available2010-08-26T13:34:34Z
dc.date.issued2009
dc.identifier.citationProceedings Interspeech 2009, pp 1791-1794en_GB
dc.identifier.urihttp://www.dspace.cam.ac.uk/handle/1810/226336
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.en_GB
dc.rightsAll Rights Reserveden
dc.rights.urihttps://www.rioxx.net/licenses/all-rights-reserved/en
dc.subjectHMM-based speech synthesisen_GB
dc.subjectunsupervised speaker adaptationen_GB
dc.titleTwo-pass decision tree construction for unsupervised adaptation of HMM-based synthesis modelsen_GB
dc.typeArticleen_GB
dc.type.versionaccepted versionen_GB
pubs.declined2017-10-11T13:54:29.69+0100


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record