@Article{kressner.16,
  author = 	 {Kressner, A.A. and May, T. and Rozell, C.J.},
  title = 	 {Outcome measures based on classification performance fail to predict the intelligibility of binary-masked speech},
  abstract =     {To date, the most commonly used outcome measure for assessing ideal binary mask estimation algorithms is based on the difference between the hit rate and the false alarm rate ({H-FA}). Recently, the error distribution has been shown to substantially affect intelligibility. However, {H-FA} treats each mask unit independently and does not take into account how errors are distributed. Alternatively, algorithms can be evaluated with the short-time objective intelligibility ({STOI}) metric using the reconstructed speech. This study investigates the ability of {H-FA} and {STOI} to predict intelligibility for binary-masked speech using masks with different error distributions. The results demonstrate the inability of {H-FA} to predict the behavioral intelligibility and also illustrate the limitations of {STOI}. Since every estimation algorithm will make errors that are distributed in different ways, performance evaluations should not be made solely on the basis of these metrics.},
year = 2016,
journal = {Journal of the Acoustical Society of America},
month = jun,
volume = {139},
number = {6}, 
pages = {3033--3036},
url = {http://scitation.aip.org/content/asa/journal/jasa/139/6/10.1121/1.4952439}
}