ADNAC: Audio Denoiser using Neural Audio Codec
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.
Cite
@article{arxiv.2511.01773,
title = {ADNAC: Audio Denoiser using Neural Audio Codec},
author = {Daniel Jimon and Mircea Vaida and Adriana Stan},
journal= {arXiv preprint arXiv:2511.01773},
year = {2025}
}
Comments
Accepted and presented at the 13th International Conference on Speech Technology and Human-Computer Dialogue (SpeD), Cluj-Napoca, Romania, October 19-22, 2025. 4 pages, 1 figure. IEEE Catalog Number: CFP2555H-USB, ISBN: 979-8-3315-7485-7