AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

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

Robin San Roman, Yossi Adi, Antoine Deleforge, Romain Serizel, Gabriel Synnaeve, Alexandre Défossez

NeurIPS 2023 · Image generation › Autoregressive and latent generation · approach: Diffusion audio synthesis · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
remove the frequency EQ processor (ablation)MBD · reconstruction 6kbpsViSQOL: 3.38 -> 3.67Improved
use linear noise schedule instead of power schedule (ablation)MBD · reconstruction 6kbpsViSQOL: 3.67 -> 2.93Hurt
use cosine noise schedule instead of power schedule (ablation)MBD · reconstruction 6kbpsViSQOL: 3.67 -> 3.29Hurt
use a single full-band model instead of four band-specific models (ablation)MBD · reconstruction 6kbpsViSQOL: 3.67 -> 3.32Hurt
remove EQ processor, effect on high-frequency Mel-SNR (ablation)MBD · reconstruction 6kbpsMel-SNR-H: 8.46 -> 9.26Improved
increase sampling steps from 10 to 20 (ablation)MBD · reconstruction 6kbpsViSQOL: 3.61 -> 3.67Improved
increase sampling steps from 20 to 500 (ablation)MBD · reconstruction 6kbpsViSQOL: 3.67 -> 3.70No clear effect
increase sampling steps from 20 to 100 (ablation)MBD · reconstruction 6kbpsViSQOL: 3.67 -> 3.64No clear effect
replace EnCodec decoder with MBD (ablation)EnCodec 6kbps · speech MUSHRAMUSHRA: 79.03 -> 84.68Improved
replace EnCodec decoder with MBDEnCodec 6kbps · music MUSHRAMUSHRA: 84.67 -> 83.61No clear effect
replace EnCodec decoder with MBDEnCodec 1.5kbps · speech MUSHRAMUSHRA: 49.51 -> 65.83Improved
replace EnCodec decoder with MBDEnCodec 3kbps · music MUSHRAMUSHRA: 85.55 -> 87.31Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy