Music Enhancement with Deep Filters: A Technical Report for The ICASSP 2024 Cadenza Challenge
This work addresses music enhancement for audio processing applications, but it is incremental as it builds on existing methods.
The authors tackled music enhancement by incorporating deep filters from DeepfilterNet into a Spec-UNet-based network to improve a hybrid Demucs pipeline, resulting in incremental improvements in Signal-to-Distortion Ratio (SDR) and Hearing Aid Audio Quality Index (HAAQI) metrics.
In this challenge, we disentangle the deep filters from the original DeepfilterNet and incorporate them into our Spec-UNet-based network to further improve a hybrid Demucs (hdemucs) based remixing pipeline. The motivation behind the use of the deep filter component lies at its potential in better handling temporal fine structures. We demonstrate an incremental improvement in both the Signal-to-Distortion Ratio (SDR) and the Hearing Aid Audio Quality Index (HAAQI) metrics when comparing the performance of hdemucs against different versions of our model.