Fig. 7From: Components loss for neural networks in mask-based speech enhancementNoise attenuation (NAseg) vs. speech component quality \((\text {PESQ}(\tilde {\mathbf {s}}))\) for different parameters α for the baseline eIRM MSE (3) on 12.5% of the validation set. From top to bottom, the markers are corresponding to six SNR conditions from 20 to −5 dB with a step size of 5 dB. The selected setting α=0.75 is in the legendBack to article page