Skip to main content
. Author manuscript; available in PMC: 2016 Dec 1.
Published in final edited form as: IEEE/ACM Trans Audio Speech Lang Process. 2016 Mar 1;24(5):967–977. doi: 10.1109/TASLP.2016.2536478

TABLE III.

STOI Comparison Between Speech Separation Methods With Multi-SNR Speaker-Pair Dependent Training on SSC Corpus

−12 dB −9 dB −6 dB −3 dB O dB 3 dB 6 dB
Noisy 46.4 52.2 58.8 65.8 72.7 79.2 84.8
DNN+Map 74.9 80.4 84.6 87.8 90.3 92.3 93.7
DNN+IRM 72.0 77.8 82.7 86.6 89.7 92.1 94.0
MCA+IRM 74.2 79.7 84.3 87.9 90.8 93.0 94.6
MCS+IRM 75.1 81.0 85.6 89.1 91.8 93.7 95.1
DNN+SA 78.9 83.5 86.9 89.6 91.8 93.6 95.0
MCA+SA 80.8 84.9 88.1 90.6 92.5 94.2 95.5
MCS+SA 81.4 85.7 88.9 91.2 93.1 94.6 95.9