Skip to main content

Advertisement

Table 1 Performance comparison of different methods in terms of WSS for white noise-corrupted speech

From: A semisoft thresholding method based on Teager energy operation on wavelet packet coefficients for enhancing noisy speech

SNR (dB) Universal threshold WPF algorithm WTHSKL method Proposed method
15 37 24.52 22.34 18.87
10 44.77 37.6 34.9 26.5
5 53.9 46.2 46.08 34.3
0 66.63 59.2 60.66 43.65
-5 83.8 71.4 76.92 52.45
-10 96 87.5 89.29 65.2
-15 104.44 91.9 90.37 77.20