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

Table 1 Best-case scenario for a single CD codebook under babble noise

From: Robust Bayesian estimation for context-based speech enhancement

 

ΔPESQ

ΔSSNR (in dB)

Input SSNR

0 dB

5 dB

10 dB

0 dB

5 dB

10 dB

CBSE with CD

0.12±0.06

0.18±0.06

0.20±0.07

6.44±0.72

6.01±0.70

4.50±0.88

CBSE with CI

−0.04±0.07

−0.01±0.06

−0.02±0.09

5.59±0.97

4.76±0.92

2.82±1.09

Proposed

0.12±0.06

0.18±0.06

0.20±0.07

6.44±0.72

6.00±0.70

4.49±0.88

Reference

−0.11±0.02

−0.11±0.02

−0.10±0.04

2.08±0.46

2.42±0.47

2.17±0.53

  1. The CD codebook is modeling two aspects of context, speaker and acoustic environment. Both mean and standard deviation values are reported.
Back to article page