Skip to main content
EURASIP Journal on Audio, Speech, and Music Processing

Table 10 Results using two CD codebooks and one CI codebook, for context match scenario for CD-2 under traffic noise

From: Robust Bayesian estimation for context-based speech enhancement

 

ΔPESQ

ΔSSNR (in dB)

Input SNR

0 dB

5 dB

10 dB

0 dB

5 dB

10 dB

CBSE with CD-1

−0.05±0.13

0.08±0.15

0.13±0.12

6.39±1.40

5.87±0.98

4.4±0.95

CBSE with CD-2

0.01±0.12

0.21±0.15

0.25±0.15

6.69±1.35

6.21±0.91

4.62±0.96

CBSE with CI

−0.07±0.14

0.09±0.16

0.19±0.16

6.48±1.37

5.80±1.02

4.17±1.03

Proposed

0.01±0.12

0.20±0.15

0.27±0.14

6.69±1.36

6.21±0.95

4.70±0.96

Reference

0.07±0.07

0.12±0.10

0.13±0.10

2.76±0.84

3.17±0.83

2.78±0.69

  1. Both mean and standard deviation values are reported.
Back to article page