In this paper, we report on an experiment that tested users ability to understand the content of spoken auditory reminders. Users heard meeting reminders and medication reminders spoken in both a natural and a synthetic voice. Our results show that older users can understand synthetic speech as well as younger users provided that the prompt texts are well-designed, using familiar words and contextual cues. As soon as unfamiliar and complex words are introduced, users hearing affects how well they can understand the synthetic voice, even if their hearing would pass common screening tests for speech synthesis experiments. Although hearing thresholds correlate best with users performance, central auditory processing may also influence performance, especially when complex errors are made.
Cite as: Wolters, M., Campbell, P., DePlacido, C., Liddell, A., Owens, D. (2007) Making speech synthesis more accessible to older people. Proc. 6th ISCA Workshop on Speech Synthesis (SSW 6), 288-293
@inproceedings{wolters07_ssw,
author={Maria Wolters and Pauline Campbell and Christine DePlacido and Amy Liddell and David Owens},
title={{Making speech synthesis more accessible to older people}},
year=2007,
booktitle={Proc. 6th ISCA Workshop on Speech Synthesis (SSW 6)},
pages={288--293}
}