When deciding whether to adapt relevant aspects of the system to the particular needs of older users, spoken dialogue systems often rely on automatic detection of chronological age. In this paper, we show that vocal ageing as measured by acoustic features is an unreliable indicator of the need for adaptation. Simple lexical features greatly improve the prediction of both relevant aspects of cognition and interactions style. Lexical features also boost age group prediction. We suggest that adaptation should be based on observed behaviour, not on chronological age, unless it is not feasible to build classifiers for relevant adaptation decisions.
Cite as: Wolters, M., Vipperla, R., Renals, S. (2009) Age recognition for spoken dialogue systems: do we need it? Proc. Interspeech 2009, 1435-1438, doi: 10.21437/Interspeech.2009-440
@inproceedings{wolters09_interspeech, author={Maria Wolters and Ravichander Vipperla and Steve Renals}, title={{Age recognition for spoken dialogue systems: do we need it?}}, year=2009, booktitle={Proc. Interspeech 2009}, pages={1435--1438}, doi={10.21437/Interspeech.2009-440} }