Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

More »

Fig 1 Expand

Fig 2.

More »

Fig 2 Expand

Table 1.

Hyperparameters of all deep learning networks.

More »

Table 1 Expand

Table 2.

STOI (in%) in matched test scores.

More »

Table 2 Expand

Table 3.

PESQ in matched test scores.

More »

Table 3 Expand

Table 4.

SDR in matched test scores.

More »

Table 4 Expand

Table 5.

Unmatched test scores in five noise sources at all SNRs.

The results are averaged over all testing utterances.

More »

Table 5 Expand

Fig 3.

More »

Fig 3 Expand

Fig 4.

More »

Fig 4 Expand

Table 6.

Comparison against non-deep learning methods.

Test Scores are averaged over five noise sources at all SNRs.

More »

Table 6 Expand

Table 7.

Unmatched test scores in five noise sources at all SNRs.

The results are averaged over all testing utterances.

More »

Table 7 Expand

Table 8.

Dynamical-Weight vs. Non-Dynamical-Weight loss.

More »

Table 8 Expand

Fig 5.

More »

Fig 5 Expand

Fig 6.

More »

Fig 6 Expand

Table 9.

WERs for different SE algorithms.

More »

Table 9 Expand

Table 10.

The subjective listener’s biodata.

More »

Table 10 Expand

Fig 7.

More »

Fig 7 Expand

Fig 8.

More »

Fig 8 Expand

Table 11.

Performance analysis of proposed SE in reverberant situations.

More »

Table 11 Expand