Skip to main content
. Author manuscript; available in PMC: 2016 Jul 21.
Published in final edited form as: J Speech Lang Hear Res. 2013 Jun 19;56(5):1416–1428. doi: 10.1044/1092-4388(2013/11-0298)

Figure 8.

Figure 8

ROC curves giving the voicing-detection performance of the system. V, VF, and HV frames were separately considered to be positives. Only UV frames were considered to be negatives. Az values were: V/(UV) = .995; HV/(UV) = .883; VF/(UV) = .934.