Fig 1.
Fig 2.
Table 1.
Hyperparameters of all deep learning networks.
Table 2.
STOI (in%) in matched test scores.
Table 3.
PESQ in matched test scores.
Table 4.
SDR in matched test scores.
Table 5.
Unmatched test scores in five noise sources at all SNRs.
The results are averaged over all testing utterances.
Fig 3.
Fig 4.
Table 6.
Comparison against non-deep learning methods.
Test Scores are averaged over five noise sources at all SNRs.
Table 7.
Unmatched test scores in five noise sources at all SNRs.
The results are averaged over all testing utterances.
Table 8.
Dynamical-Weight vs. Non-Dynamical-Weight loss.
Fig 5.
Fig 6.
Table 9.
WERs for different SE algorithms.
Table 10.
The subjective listener’s biodata.
Fig 7.
Fig 8.
Table 11.
Performance analysis of proposed SE in reverberant situations.