How can we provide feedback to second language (L2) learners regarding the goodness of their productions in an automatic way? In this paper, we introduce our two attempts to provide effective feedback to adults learning to produce speech segments in an L2. First, we adopted visualized acoustic properties as feedback in a computer-based L2 training system. Second, we investigated the correlation between human judgments of L2 production quality and acoustic scores produced by an HMM-based speech recognition system. The results are discussed in the context of optimizing L2 speech training.
Cite as: Akahane-Yamada, R., Adachi, T., Kawahara, H., Pruitt, J.S., McDermott, E. (1998) Toward the optimization of computer-based second language production training. Proc. ETRW on Speech Technology in Language Learning (STiLL), 111-114
@inproceedings{akahaneyamada98_still,
author={Reiko Akahane-Yamada and Takahiro Adachi and Hideki Kawahara and John S. Pruitt and Erik McDermott},
title={{Toward the optimization of computer-based second language production training}},
year=1998,
booktitle={Proc. ETRW on Speech Technology in Language Learning (STiLL)},
pages={111--114}
}