Skip to main content

Table 4 segSNR improvement comparisons of DD + VAD, DD+ [19], and proposed algorithms

From: A priori SNR estimation and noise estimation for speech enhancement

Noise

0 dB

5 dB

10 dB

DD + VAD

DD+[19]

Proposed

DD + VAD

DD+[19]

Proposed

DD + VAD

DD+[19]

Proposed

Babble

2.552

2.797

2.964

2.204

2.190

2.571

1.774

1.594

1.992

Car

4.467

4.111

4.649

3.934

3.503

4.085

3.263

2.889

3.219

Exhibition

3.433

3.370

3.764

2.936

2.906

3.324

2.328

2.340

2.703

Station

3.532

3.472

3.794

3.057

2.802

3.194

2.506

2.150

2.587

White

5.245

4.702

5.417

4.887

4.088

4.833

4.211

3.617

4.091

  1. The numbers in italics indicate the best performance. And all the results are the segSNR improvement compared to that of the untreated noisy speech