HMM-based speech synthesis with an acoustic glottal source model
File Type:
PDFItem Type:
Conference PaperDate:
2009Access:
openAccessCitation:
Cabral, J.P., Renals, S., Richmond, K. & Yamagishi, J., HMM-based speech synthesis with an acoustic glottal source model, The First Young Researchers Workshop in Speech Technology, Dublin, Ireland, 25 April, 2009Download Item:
Abstract:
A major cause of degradation of speech quality in HMMbased
speech synthesis is the use of a simple delta pulse signal
to generate the excitation of voiced speech.
This paper describes a new approach to using an acoustic
glottal source model in HMM-based synthesisers. The goal is
to improve speech quality and parametric flexibility to better
model and transform voice characteristics.
Sponsor
Grant Number
Marie Curie
MEST-CT-2005-020568
Author's Homepage:
http://people.tcd.ie/cabraljSponsor:
Marie CurieOther Titles:
The First Young Researchers Workshop in Speech TechnologyType of material:
Conference PaperCollections
Availability:
Full text availableSubject (TCD):
Creative Technologies , Speech synthesis , VOICE SOURCEMetadata
Show full item recordLicences: