Pleasant singing voice is often ornamented by vibrato. This pitch fluctuation acts as a distinctive feature for singing and promotes voice quality. Nevertheless, independent pitch processing in singing voice synthesis does not guarantee the output quality. The spectral envelope actually varies with pitch during human voice production. This paper proposes a modeling technique for singers' vibratos, followed by a joint processing on vibrato and spectral envelope, such that these attributes are consistent. The performance of the proposed processing has been verified by subjective listening test. The synthetic singing outputs are found to have similar quality as the human singing.
Cite as: Lee, S.W., Dong, M. (2011) Singing voice synthesis: singer-dependent vibrato modeling and coherent processing of spectral envelope. Proc. Interspeech 2011, 2001-2004, doi: 10.21437/Interspeech.2011-526
@inproceedings{lee11e_interspeech,
author={S. W. Lee and Minghui Dong},
title={{Singing voice synthesis: singer-dependent vibrato modeling and coherent processing of spectral envelope}},
year=2011,
booktitle={Proc. Interspeech 2011},
pages={2001--2004},
doi={10.21437/Interspeech.2011-526}
}