Skip to main content
. Author manuscript; available in PMC: 2020 Jul 13.
Published in final edited form as: IEEE Access. 2019 Jun 12;7:78421–78433. doi: 10.1109/access.2019.2922370

TABLE 2.

Illustration of the effect of dropout on the proposed CNN-based SE model. Speech data with Machinery noise at 0db SNR was considered.

Dropout (%) PESQ LSD SegSNR
0 2.1855 11.9056 6.7691
10 2.1684 11.6541 6.7420
20 2.1062 11.9294 6.6951
30 2.0050 12.2047 6.6240