We describe a voice response unit embedded in FA systems and a Japanese voice synthesis technique using synthesis-by-rule, where prosodic information such as duration, stress, and pitch are combined with phonemic information such as CV syllables (Japanese syllables). The unit has a compact and user-extensible speech database and yields natural sounding synthetic speech.
Cite as: Yamamura, A., Kunizawa, H., Ueji, N., Itoyama, H., Kakusho, O. (1990) Voice response unit embedded in factory automation systems. Proc. First International Conference on Spoken Language Processing (ICSLP 1990), 845-848, doi: 10.21437/ICSLP.1990-109
@inproceedings{yamamura90_icslp,
author={Akira Yamamura and Hiroharu Kunizawa and Noboru Ueji and Hiroshi Itoyama and Osamu Kakusho},
title={{Voice response unit embedded in factory automation systems}},
year=1990,
booktitle={Proc. First International Conference on Spoken Language Processing (ICSLP 1990)},
pages={845--848},
doi={10.21437/ICSLP.1990-109}
}