Outlier removal is a straightforward technique for improving the quality of unit selection catalogs without hand correction. This paper investigates the use of phone durations as a criteria for removing bad units. Scoring conditioned on linguistic context demonstrably better than statistics based on phone class alone. The impact of voice modification is evaluated with a 444K utterance test corpus.
Cite as: Kominek, J., Black, A.W. (2004) Impact of durational outlier removal from unit selection catalogs. Proc. 5th ISCA Workshop on Speech Synthesis (SSW 5), 155-160
@inproceedings{kominek04_ssw,
author={John Kominek and Alan W. Black},
title={{Impact of durational outlier removal from unit selection catalogs}},
year=2004,
booktitle={Proc. 5th ISCA Workshop on Speech Synthesis (SSW 5)},
pages={155--160}
}