7th International Conference on Spoken Language Processing

September 16-20, 2002
Denver, Colorado, USA

Evaluation of Cross-Language Voice Conversion Using Bilingual and Non-Bilingual Databases

Mikiko Mashimo, Tomoki Toda, Hiromichi Kawanami, Hideki Kashioka, Kiyohiro Shikano, Nick Campbell

Nara Institute of Science and Technology, Japan

Cross-language voice conversion is useful for many applications, and we are trying to apply the technique to a language training system for reducing voice individuality differences. In this paper, we describe experiments that test effectiveness of an extension of singlelanguage voice conversion, to include cross-language utterances. The performance was investigated by objective and perceptual evaluation using bilingual-speakers data for training. Then, the correlations between a computed distance measure and a human perceptual pronunciation evaluation score were compared before and after applying conversion. From these results, it was found that the crosslanguage voice conversion reduces speakers’ voice differences between the pairs, and the phoneme based measures show somewhat clearer correspondences to the human perceptual score in vowels’ test after applying voice conversion.

Full Paper

Bibliographic reference.  Mashimo, Mikiko / Toda, Tomoki / Kawanami, Hiromichi / Kashioka, Hideki / Shikano, Kiyohiro / Campbell, Nick (2002): "Evaluation of cross-language voice conversion using bilingual and non-bilingual databases", In ICSLP-2002, 293-296.