Skip to main content
EURASIP Journal on Advances in Signal Processing

Table 1 segSNR improvement comparisons of DDBSE and DD using MCRA

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

Noise

0 dB

5 dB

10 dB

DD

DDBSE

DD

DDBSE

DD

DDBSE

Babble

2.774

2.885

2.400

2.519

1.960

2.021

Car

4.300

4.536

3.831

3.972

3.050

3.075

Exhibition

3.558

3.716

3.102

3.238

2.434

2.478

Station

3.457

3.637

3.006

3.132

2.445

2.468

White

5.082

5.367

4.600

4.771

3.846

3.850

Average

3.834

4.028

3.388

3.526

2.747

2.778

  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
Back to article page