Skip to main content
. Author manuscript; available in PMC: 2011 Sep 8.
Published in final edited form as: IEEE Trans Audio Speech Lang Process. 2011;19(1):47–56. doi: 10.1109/TASL.2010.2045180

Figure 4.

Figure 4

Results, expressed in percentage of words identified correctly, from the intelligibility studies with human listeners. The bars indicated as “UN” show the scores obtained with noise-corrupted (un-processed) stimuli, while the bars indicated as “SE” show the baseline scores obtained with the three enhancement algorithms (no constraints imposed). The intelligibility scores obtained with speech processed by the three enhancement algorithms after imposing four different constraints are labeled accordingly.