Table 9 Results using two CD codebooks and one CI codebook, for context match scenario for CD-1 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 | 0.07±0.17 | 0.24±0.17 | 0.25±0.18 | 6.67±1.67 | 5.70±1.62 | 3.76±1.50 |
CBSE with CD-2 | −0.16±0.16 | −0.03±0.17 | −0.03±0.19 | 6±1.78 | 4.49±1.82 | 1.88±2.00 |
CBSE with CI | −0.1±0.18 | 0.01±0.16 | 0.03±0.17 | 5.85±1.76 | 4.53±1.87 | 2.06±1.84 |
Proposed | 0.06±0.16 | 0.20±0.19 | 0.22±0.21 | 6.58±1.68 | 5.44±1.65 | 3.19±1.61 |
Reference | 0.05±0.07 | 0.11±0.09 | 0.17±0.11 | 2.54±0.85 | 2.96±0.91 | 2.71±1.02 |