Skip to main content
. Author manuscript; available in PMC: 2015 Mar 1.
Published in final edited form as: Comput Speech Lang. 2012 Oct 4;28(2):10.1016/j.csl.2012.09.004. doi: 10.1016/j.csl.2012.09.004

Figure 2.

Figure 2

Recall and prediction per speaker plotted against each speaker’s BAC for final model– trained on matched-prompt train&devel sets and evaluated on the official test set.