ISCA Archive Interspeech 2009
ISCA Archive Interspeech 2009

Many-to-many eigenvoice conversion with reference voice

Yamato Ohtani, Tomoki Toda, Hiroshi Saruwatari, Kiyohiro Shikano

In this paper, we propose many-to-many voice conversion (VC) techniques to convert an arbitrary source speaker’s voice into an arbitrary target speaker’s voice. We have proposed one-to-many eigenvoice conversion (EVC) and many-to-one EVC. In the EVC, an eigenvoice Gaussian mixture model (EV-GMM) is trained in advance using multiple parallel data sets of a reference speaker and many pre-stored speakers. The EV-GMM is flexibly adapted to an arbitrary speaker using a small amount of adaptation data without any linguistic constraints. In this paper, we achieve many-to-many VC by sequentially performing many-to-one EVC and one-to-many EVC through the reference speaker using the same EV-GMM. Experimental results demonstrate the effectiveness of the proposed many-to-many VC.


doi: 10.21437/Interspeech.2009-485

Cite as: Ohtani, Y., Toda, T., Saruwatari, H., Shikano, K. (2009) Many-to-many eigenvoice conversion with reference voice. Proc. Interspeech 2009, 1623-1626, doi: 10.21437/Interspeech.2009-485

@inproceedings{ohtani09_interspeech,
  author={Yamato Ohtani and Tomoki Toda and Hiroshi Saruwatari and Kiyohiro Shikano},
  title={{Many-to-many eigenvoice conversion with reference voice}},
  year=2009,
  booktitle={Proc. Interspeech 2009},
  pages={1623--1626},
  doi={10.21437/Interspeech.2009-485}
}