Show simple item record

dc.contributor.authorShannon, SM
dc.contributor.authorByrne, WJ
dc.date.accessioned2010-09-10T16:57:01Z
dc.date.available2010-09-10T16:57:01Z
dc.date.issued2009
dc.identifier.citationM. Shannon and W. Byrne, "Autoregressive HMMs for speech synthesis," in Proc. Interspeech 2009, 2009, pp 400-403, http://mi.eng.cam.ac.uk/~sms46/papers/shannon2009ahs.pdf
dc.identifier.urihttp://www.dspace.cam.ac.uk/handle/1810/226373
dc.description.abstractWe propose the autoregressive HMM for speech synthesis. We show that the autoregressive HMM supports efficient EM parameter estimation and that we can use established effective synthesis techniques such as synthesis considering global variance with minimal modification. The autoregressive HMM uses the same model for parameter estimation and synthesis in a consistent way, in contrast to the standard HMM synthesis framework, and supports easy and efficient parameter estimation, in contrast to the trajectory HMM. We find that the autoregressive HMM gives performance comparable to the standard HMM synthesis framework on a Blizzard Challenge-style naturalness evaluation.
dc.description.sponsorshipThis research was funded by the European Community's Seventh Framework Programme (FP7/2007-2013), grant agreement 213845 (EMIME).
dc.format.mediumpaper
dc.language.isoen
dc.publisherISCA (International Speech Communication Association)
dc.rightsAttribution 2.0 UK: England & Wales
dc.rights.urihttp://creativecommons.org/licenses/by/2.0/uk/
dc.titleAutoregressive HMMs for speech synthesis
dc.typeConference Object
prism.publicationDate2009
rioxxterms.licenseref.urihttp://www.rioxx.net/licenses/all-rights-reserved
rioxxterms.licenseref.startdate2009
rioxxterms.typeConference Paper/Proceeding/Abstract
pubs.conference-name10th International Conference of the International Speech Communication Association, Interspeech 2009
pubs.conference-start-date2009-09-06
pubs.conference-finish-date2009-09-10


Files in this item

Thumbnail
Thumbnail
Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record

Attribution 2.0 UK: England & Wales
Except where otherwise noted, this item's licence is described as Attribution 2.0 UK: England & Wales