AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

BDDM: Bilateral Denoising Diffusion Models for Fast and High-Quality Speech Synthesis

Max W. Y. Lam, Jun Wang, Dan Su, Dong Yu

ICLR 2022 · Image generation › Fast diffusion sampling · approach: Denoising diffusion probabilistic models · 26 citations (OpenAlex)

Read the paper

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
Use BDDM's learned schedule instead of grid searchthe same score network · LJSpeech, 3 stepsMOS: 3.61±0.12 -> 3.64±0.13No clear effect
Use BDDM's learned schedule instead of NEthe same score network · LJSpeech, 7 stepsMOS: 4.02±0.11 -> 4.43±0.11Improved
Use BDDM's learned schedule instead of DDIMthe same score network · LJSpeech, 12 stepsMOS: 4.16±0.12 -> 4.48±0.12Improved
Replace the proposed schedule-network loss with the standard negative ELBO (ablation)BDDM schedule network · LJSpeechnoise-scale prediction stabilityHurt
Train the schedule network after optimizing the score networkBDDM · LJSpeechlower-bound tightnessImproved

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