ADNAC: Audio Denoiser using Neural Audio Codec
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 13 of its 30 references that are in the map. First posted on arXiv 3 Nov 2025.
Builds on
13 of 30 references.
References · 13
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
- 2021SoundStream: An End-to-End Neural Audio Codeccited by 756
- 2023High-Fidelity Audio Compression with Improved RVQGANcited by 423
- 2018SDR - half-baked or well done?cited by 420
- 2015MUSAN: A Music, Speech, and Noise Corpuscited by 400
- 2020FSD50K: An Open Dataset of Human-Labeled Sound Eventscited by 339
- 2022Speech Enhancement and Dereverberation with Diffusion-based Generative Modelscited by 195
- 2022CMGAN: Conformer-based Metric GAN for Speech Enhancementcited by 45
- 2018Building and Evaluation of a Real Room Impulse Response Datasetcited by 43
- 2021DPT-FSNet: Dual-path Transformer Based Full-band and Sub-band Fusion Network for Speech Enhancementcited by 33
- 2024Diffusion Models for Audio Restorationcited by 32
- 2018Improved Speech Enhancement with the Wave-U-Netcited by 23
1 more
- 2020Learning to Denoise Historical Musiccited by 8
Built on by
Not cited yet.