Unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis using two-pass decision tree construction
Change log
Authors
Gibson, M
Hirsimaki, T
Karhila, R
Kurimo, M
Byrne, WJ
Abstract
This paper demonstrates how unsupervised cross-lingual adaptation of HMM-based speech synthesis models may be performed without explicit knowledge of the adaptation data language. A two-pass decision tree construction technique is deployed for this purpose. Using parallel translated datasets, cross-lingual and intralingual adaptation are compared in a controlled manner. Listener evaluations reveal that the proposed method delivers performance approaching that of unsupervised intralingual adaptation.
Description
Keywords
HMM-based speech synthesis, unsupervised speaker adaptation, cross-lingual
Journal Title
Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing
Conference Name
IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP' 10
Journal ISSN
Volume Title
Publisher
IEEE
Publisher DOI
Sponsorship
European Commission (213845)