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

Table 4.

Unweighted average recall on the matched prompts and the non-matched prompts in reference to matched and non-matched prompt training. Global speaker normalization is used.

Tested on:
Non-matched Matched
Trained on: Official 0.771 0.658
Matched N/A 0.697