Unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis using two-pass decision tree construction
View / Open Files
Authors
Gibson, M
Hirsimaki, T
Karhila, R
Kurimo, M
Byrne, WJ
Publication Date
2010Journal 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
ISBN
9781424442959
Publisher
IEEE
Pages
4642-4645
Type
Conference Object
Physical Medium
paper
Metadata
Show full item recordCitation
Gibson, M., Hirsimaki, T., Karhila, R., Kurimo, M., & Byrne, W. (2010). Unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis using two-pass decision tree construction. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, 4642-4645. https://doi.org/10.1109/ICASSP.2010.5495196
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.
Sponsorship
European Commission (213845)
Identifiers
External DOI: https://doi.org/10.1109/ICASSP.2010.5495196
This record's URL: http://www.dspace.cam.ac.uk/handle/1810/226329
Rights
Licence:
http://www.rioxx.net/licenses/all-rights-reserved
Statistics