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

FIGURE 7.

FIGURE 7.

Comparison of average performance of PESQ, LSD, and SegSNR on seen and unseen data for different SE methods. Machinery, multi-talker babble and traffic noise at SNR levels of −5, 0 and +5dB are considered. The results show that the proposed CNN-based SE method outperforms the other SE methods.