In this paper an efficient segment selection method for corpus-based speech synthesis is presented. Traditional unit-selectors use dynamic programming (DP) to find in a fully connected segment network the most appropriate segment sequence based on target- and concatenation costs. Instead of performing a full DP search, the presented unit-selector applies fast transformations on binary valued segment connection matrices. It is further also shown that this technique can be expanded to supra-segmental unit-selection without altering the segment size in the database.
Cite as: Coorman, G. (2006) Segment connection networks for corpus-based speech synthesis. Proc. Interspeech 2006, paper 1962-Wed3BuP.13, doi: 10.21437/Interspeech.2006-408
@inproceedings{coorman06_interspeech, author={Geert Coorman}, title={{Segment connection networks for corpus-based speech synthesis}}, year=2006, booktitle={Proc. Interspeech 2006}, pages={paper 1962-Wed3BuP.13}, doi={10.21437/Interspeech.2006-408} }