We present in this work a strategy to perform timbre conversion from un- paired source and target data and its application to the singing-voice synthe- sizer VOCALOID to produce sung utterances with a past singer voice. The conversion framework using unpaired data is based on a phoneme-constrained modeling of the timbre space and the assumption of a linear relation between the source and target features. The proposed nonparallel framework resulted in a performance close to the one following the traditional approach based on GMM and paired data. The application to convert an original singer database using sung performances of a past singer observed a successful perception of the past singer..s timbre on the singing-voice utterances performed by VOCALOID.
Cite as: Villavicencio, F., Kenmochi, H. (2010) Resurrecting past singers: non-parallel singing-voice conversion. Proc. First Interdisciplinary Workshop on Singing Voice (InterSinging 2010), 39-44
@inproceedings{villavicencio10_intersinging,
author={Fernando Villavicencio and Hideki Kenmochi},
title={{Resurrecting past singers: non-parallel singing-voice conversion}},
year=2010,
booktitle={Proc. First Interdisciplinary Workshop on Singing Voice (InterSinging 2010)},
pages={39--44}
}