Unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis using two-pass decision tree construction

Download: PDF, poster.

“Unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis using two-pass decision tree construction” by M. Gibson, T. Hirsimaki, R. Karhila, M. Kurimo, and W. Byrne. In Proceedings of IEEE Conference on Acoustics, Speech and Signal Processing, 2010, pp. 4642 -- 4645 (4 pages).

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.

Download: PDF, poster.

BibTeX entry:

@inproceedings{Gibson2010,
   author = {M. Gibson and T. Hirsimaki and R. Karhila and M. Kurimo and
	W. Byrne},
   title = {Unsupervised cross-lingual speaker adaptation for {HMM}-based
	speech synthesis using two-pass decision tree construction},
   booktitle = {Proceedings of IEEE Conference on Acoustics, Speech and
	Signal Processing},
   pages = {4642 -- 4645 (4 pages)},
   year = {2010}
}

Back to Bill Byrne publications.