We recorded non-native English productions of 55 speakers; a subset of these productions was assessed by 60 native English speakers as for their quality w. r. t. intelligibility, rhythm, etc. Applying multiple linear regression on a large prosodic feature vector – modelling approaches known from the literature as well as generic prosody – we can automatically predict the listener's assessments with correlations of up to .85. We discuss most important features and limitations of this approach.
Index Terms: non-native prosody, rhythm, intelligibility, foreign accent, linear correlation
Cite as: Hönig, F., Batliner, A., Weilhammer, K., Nöth, E. (2010) Automatic assessment of non-native prosody for English as L2. Proc. Speech Prosody 2010, paper 973
@inproceedings{honig10_speechprosody,
author={Florian Hönig and Anton Batliner and Karl Weilhammer and Elmar Nöth},
title={{Automatic assessment of non-native prosody for English as L2}},
year=2010,
booktitle={Proc. Speech Prosody 2010},
pages={paper 973}
}