In this paper, we present linear transformation algorithms for many-to-one voice conversion (VC). Many-to-one VC is a technique for converting an arbitrary source speaker’s voice into the target speaker’s voice. A conversion model previously developed between many prestored source speakers and the target speaker is adapted into a new source speaker in an unsupervised manner. In this study, we implement several well-known model adaptation techniques based on linear transformation for many-to-one VC and evaluate their effectiveness.
Index Terms: many-to-one voice conversion, Gaussian mixture model, unsupervised adaptation, linear transformation
Cite as: Hayashida, C., Toda, T., Ohtani, Y., Saruwatari, H., Shikano, K. (2010) Linear transformation approaches to many-to-one voice conversion. Proc. 7th ISCA Workshop on Speech Synthesis (SSW 7), 74-79
@inproceedings{hayashida10_ssw,
author={Chie Hayashida and Tomoki Toda and Yamato Ohtani and Hiroshi Saruwatari and Kiyohiro Shikano},
title={{Linear transformation approaches to many-to-one voice conversion}},
year=2010,
booktitle={Proc. 7th ISCA Workshop on Speech Synthesis (SSW 7)},
pages={74--79}
}