Vasily Zadorozhnyy — accepted AI-conference papers

2025

CorrGAN: Simultaneous Learning of Speech Enhancement and Perceptual Quality Loss Functions

Vasily Zadorozhnyy, Saeed Amizadeh, Qiang Ye, Kazuhito Koishida

ICASSP 2025accepted

Deep-learning models have allowed effective end-to-end SE systems in the Speech Enhancement (SE) field. Most of these methods are trained using a fixed reconstruction loss in a supervised setting. Often these losses do not perfectly represent the desired perceptual quality metrics, resulting in sub-…

Cited by 0 Source ↗Scholar ↗

2021

Adaptive Weighted Discriminator for Training Generative Adversarial Networks

Vasily Zadorozhnyy, Qiang Cheng, Qiang Ye

CVPR 2021poster

Generative adversarial network (GAN) has become one of the most important neural network models for classical unsupervised machine learning. A variety of discriminator loss functions have been developed to train GAN's discriminators and they all have a common structure: a sum of real and fake losses…

Cited by 20 PDF ↗code ↗Scholar ↗