From Discrete Tokens to High-Fidelity Audio Using Multi-Band Diffusion - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2023

From Discrete Tokens to High-Fidelity Audio Using Multi-Band Diffusion


Deep generative models can generate high-fidelity audio conditioned on various types of representations (e.g., mel-spectrograms, Mel-frequency Cepstral Coefficients (MFCC)). Recently, such models have been used to synthesize audio waveforms conditioned on highly compressed representations. Although such methods produce impressive results, they are prone to generate audible artifacts when the conditioning is flawed or imperfect. An alternative modeling approach is to use diffusion models. However, these have mainly been used as speech vocoders (i.e., conditioned on mel-spectrograms) or generating relatively low sampling rate signals. In this work, we propose a high-fidelity multi-band diffusion-based framework that generates any type of audio modality (e.g., speech, music, environmental sounds) from low-bitrate discrete representations. At equal bit rate, the proposed approach outperforms state-of-the-art generative techniques in terms of perceptual quality. Training and, evaluation code, along with audio samples, are available on the facebookresearch/audiocraft Github page.
Fichier principal
Vignette du fichier
2308.02560.pdf (15.21 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04385071 , version 1 (10-01-2024)




Robin San Roman, Yossi Adi, Antoine Deleforge, Romain Serizel, Gabriel Synnaeve, et al.. From Discrete Tokens to High-Fidelity Audio Using Multi-Band Diffusion. NeurIPS 2023 - Conference on Neural Information Processing Systems, Dec 2023, New Orleans, United States. ⟨10.48550/arXiv.2308.02560⟩. ⟨hal-04385071⟩
51 View
17 Download



Gmail Mastodon Facebook X LinkedIn More