The Seventh ISCA Tutorial and Research Workshop on Speech Synthesis

Kyoto, Japan
September 22-24, 2010

Linear Transformation Approaches to Many-to-One Voice Conversion

Chie Hayashida, Tomoki Toda, Yamato Ohtani, Hiroshi Saruwatari, Kiyohiro Shikano

Graduate School of Information Science, Nara Institute of Science and Technology (NAIST), Japan

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

Full Paper

Bibliographic reference.  Hayashida, Chie / Toda, Tomoki / Ohtani, Yamato / Saruwatari, Hiroshi / Shikano, Kiyohiro (2010): "Linear transformation approaches to many-to-one voice conversion", In SSW7-2010, 74-79.