Autoregressive HMMs for speech synthesis
View / Open Files
Authors
Shannon, SM
Byrne, WJ
Publication Date
2009Conference Name
10th International Conference of the International Speech Communication Association, Interspeech 2009
Publisher
ISCA (International Speech Communication Association)
Language
English
Type
Conference Object
Physical Medium
paper
Metadata
Show full item recordCitation
Shannon, S., & Byrne, W. (2009). Autoregressive HMMs for speech synthesis. 10th International Conference of the International Speech Communication Association, Interspeech 2009. http://www.dspace.cam.ac.uk/handle/1810/226373
Abstract
We 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.
Sponsorship
This research was funded by the European Community's Seventh Framework Programme (FP7/2007-2013), grant agreement 213845 (EMIME).
Identifiers
This record's URL: http://www.dspace.cam.ac.uk/handle/1810/226373
Rights
Attribution 2.0 UK: England & Wales
Licence URL: http://creativecommons.org/licenses/by/2.0/uk/
Statistics
Recommended or similar items
The following licence files are associated with this item: