Automatically evaluating pronunciation quality of non-native speech has seen tremendous success in both research and commercial settings, with applications in L2 learning. In this paper, submitted for the INTERSPEECH 2015 Degree of Nativeness Sub-Challenge, this problem is posed under a challenging cross-corpora setting using speech data drawn from multiple speakers from a variety of language backgrounds (L1) reading different English sentences. Since the perception of non-nativeness is realized at the segmental and suprasegmental linguistic levels, we explore a number of acoustic cues at multiple time scales. We experiment with both data-driven and knowledge-inspired features that capture degree of nativeness from pauses in speech, speaking rate, rhythm/stress, and goodness of phone pronunciation. One promising finding is that highly accurate automated assessment can be attained using a small diverse set of intuitive and interpretable features. Performance is further boosted by smoothing scores across utterances from the same speaker; our best system significantly outperforms the challenge baseline.
Cite as: Black, M.P., Bone, D., Skordilis, Z.I., Gupta, R., Xia, W., Papadopoulos, P., Chakravarthula, S.N., Xiao, B., Segbroeck, M.V., Kim, J., Georgiou, P.G., Narayanan, S.S. (2015) Automated evaluation of non-native English pronunciation quality: combining knowledge- and data-driven features at multiple time scales. Proc. Interspeech 2015, 493-497, doi: 10.21437/Interspeech.2015-182
@inproceedings{black15_interspeech,
author={Matthew P. Black and Daniel Bone and Zisis Iason Skordilis and Rahul Gupta and Wei Xia and Pavlos Papadopoulos and Sandeep Nallan Chakravarthula and Bo Xiao and Maarten Van Segbroeck and Jangwon Kim and Panayiotis G. Georgiou and Shrikanth S. Narayanan},
title={{Automated evaluation of non-native English pronunciation quality: combining knowledge- and data-driven features at multiple time scales}},
year=2015,
booktitle={Proc. Interspeech 2015},
pages={493--497},
doi={10.21437/Interspeech.2015-182}
}