Redirecting to original paper in 30 seconds...
Click below to go immediately or wait for automatic redirect
📄 Abstract
Abstract: Audio denoising is critical in signal processing, enhancing intelligibility
and fidelity for applications like restoring musical recordings. This paper
presents a proof-of-concept for adapting a state-of-the-art neural audio codec,
the Descript Audio Codec (DAC), for music denoising. This work overcomes the
limitations of traditional architectures like U-Nets by training the model on a
large-scale, custom-synthesized dataset built from diverse sources. Training is
guided by a multi objective loss function that combines time-domain, spectral,
and signal-level fidelity metrics. Ultimately, this paper aims to present a PoC
for high-fidelity, generative audio restoration.
Authors (3)
Daniel Jimon
Mircea Vaida
Adriana Stan
Submitted
November 3, 2025
Key Contributions
Presents a proof-of-concept for adapting a state-of-the-art neural audio codec (DAC) for music denoising. It overcomes limitations of U-Nets by training on a large, custom dataset with a multi-objective loss function, aiming for high-fidelity, generative audio restoration.
Business Value
Enables the restoration of old or noisy audio recordings, improving the quality of music archives, podcasts, and historical audio, creating new value from existing content.