Skip to main content

Table 4 Speech quality in terms of SRMR for simulated and real reverberated speech samples through architecture depth for REVERB-Dev dataset. The last rows represents the mean and standard deviation along the experiments presented for each column

From: Progressive loss functions for speech enhancement with deep neural networks

   Reference systems   Progressive systems    
Condition Blocks depth CNN ResNet P-CNN with WP P-CNN with UP P-ResNet with WP P-ResNet with UP
Simulated 8 7.33 8.23 6.49 7.53 8.31 7.91
  16 7.60 8.27 8.96 7.70 8.41 8.05
  24 8.87 8.14 6.18 8.09 8.03 8.02
  32 7.01 8.56 7.65 7.41 7.98 7.78
Real 8 6.05 6.82 4.90 6.32 7.06 6.91
  16 5.98 5.81 3.74 7.26 7.14 6.85
  24 4.76 5.77 2.07 6.90 6.53 6.91
  32 3.35 6.33 2.33 6.34 5.97 6.62
AVG5 ±STD 8 6.69 ±0.64 7.52 ±0.70 5.69 ±0.79 6.92 ±0.60 7.68 ±0.62 7.41 ±0.50
  16 6.79 ±0.81 7.04 ±1.23 6.35 ±2.61 7.48 ±0.22 7.77 ±0.63 7.45 ±0.60
  24 6.81 ±2.05 6.97 ±1.16 4.12 ±2.05 7.49 ±0.59 7.28 ±0.75 7.46 ±0.55
  32 5.18 ±1.83 7.44 ±1.11 4.99 ±2.66 6.87 ±0.53 6.97 ±1.00 7.20 ±0.58
  1. Bold values show the best result for each condition