Success Story - en

Reducing noise in audio recordings

Project context and description:
Improving the quality of noise reduction models in the case of extremely low SNR (signal-to-noise ratio).

Main issues:
If the signal is highly noisy, the task of restoring the original signal becomes more difficult, since part of the signal is irretrievably damaged.

We modified the models, used the DeepFeatureLoss approach and combined different losses. We used Gans to restore (generate) a signal lost due to noise.

Improved SDR and PESQ for cleaned files compared to noisy files.

Technology stack:
Pytorch, Demucs, WaveUNet, DCUNet, ConvTasNet, Hifi-GAN, UNet-GAN, etc.
Research Audio
Made on