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

Table 3 Best-case scenario for a single CD codebook under traffic 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

0.00±0.30

0.19±0.06

0.25±0.11

7.84±1.08

6.97±1.11

5.40±1.35

CBSE with CI

−0.21±0.29

−0.05±0.10

0.00±0.14

6.67±1.37

5.57±1.29

3.64±1.49

Proposed

0.01±0.30

0.19±0.06

0.26±0.11

7.83±1.09

6.96±1.11

5.39±1.35

Reference

−0.04±0.31

0.08±0.05

0.08±0.06

2.75±0.49

2.82±0.54

2.21±0.79

  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