"Evalution of cross-language voice conversion using bilingual and 
non-bilingual databases"
Mikiko Mashimo

I will present our work that test an extension of a single-
language voice conversion technique to a cross-language conversion.
Voice conversion means converting the voice of one speaker to sound
like that of another speaker, and it is useful for many applications if
it is extended to cross-languages. To modify source speeches, we
concentrated on reducing spectral and f0 differences between the speakers.
The performance was investigated by objective and perceptual evaluation
using Japanese and English bilingual-speakers data for training in a
system based on a Gaussian mixture model and a high quality vocoder.
Results indicate that training with cross-language models also reduces
speaker's voice diffrences between the pairs. Some demonstrations and
future work are also included in the talk.