Distortion Audio Effects: Learning How to Recover the Clean Signal
This work addresses the need for automated remixing systems in music production, though it is incremental as it builds on existing neural network approaches for source separation and audio effect modeling.
The paper tackled the problem of removing distortion audio effects from guitar tracks in music production, achieving better quality and significantly faster inference compared to state-of-the-art sparse optimization methods.
Given the recent advances in music source separation and automatic mixing, removing audio effects in music tracks is a meaningful step toward developing an automated remixing system. This paper focuses on removing distortion audio effects applied to guitar tracks in music production. We explore whether effect removal can be solved by neural networks designed for source separation and audio effect modeling. Our approach proves particularly effective for effects that mix the processed and clean signals. The models achieve better quality and significantly faster inference compared to state-of-the-art solutions based on sparse optimization. We demonstrate that the models are suitable not only for declipping but also for other types of distortion effects. By discussing the results, we stress the usefulness of multiple evaluation metrics to assess different aspects of reconstruction in distortion effect removal.