ADNAC: Audio Denoiser using Neural Audio Codec
This addresses noise reduction in musical recordings for audio processing applications, but it is incremental as it adapts an existing codec.
The paper tackled audio denoising for music by adapting a neural audio codec, achieving a proof-of-concept for high-fidelity restoration through training on a custom dataset with a multi-objective loss.
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.