This paper describes a new concatenative TTS system under development at ATR. The system, named XIMERA, is based on corpus-based technologies, as was the case for the preceding TTS systems from ATR, namely í-talk and CHATR. The prominent features of XIMERA are (1) large corpora (a 110-hours corpus of a Japanese male, a 60-hours corpus of a Japanese female, and a 20-hours corpus of a Chinese female), (2) HMM-based generation of prosodic parameters, and (3) a cost function for segment selection optimized based on perceptual experiments. A perception test that evaluated the naturalness of synthetic speech for XIMERA and 10 TTS products, including CHATR, showed that XIMERA outperformed the other ten.
Cite as: Kawai, H., Toda, T., Ni, J., Minoru, M., Tsuzaki, T., Tokuda, K. (2004) XIMERA: a new TTS from ATR based on corpus-based technologies. Proc. 5th ISCA Workshop on Speech Synthesis (SSW 5), 179-184
@inproceedings{kawai04_ssw,
author={Hisashi Kawai and Tomoki Toda and Jinfu Ni and Minoru Minoru and Tsuzaki Tsuzaki and Keiichi Tokuda},
title={{XIMERA: a new TTS from ATR based on corpus-based technologies}},
year=2004,
booktitle={Proc. 5th ISCA Workshop on Speech Synthesis (SSW 5)},
pages={179--184}
}