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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use BDDM's learned schedule instead of grid search | the same score network · LJSpeech, 3 steps | MOS: 3.61±0.12 -> 3.64±0.13 | No clear effect |
| Use BDDM's learned schedule instead of NE | the same score network · LJSpeech, 7 steps | MOS: 4.02±0.11 -> 4.43±0.11 | Improved |
| Use BDDM's learned schedule instead of DDIM | the same score network · LJSpeech, 12 steps | MOS: 4.16±0.12 -> 4.48±0.12 | Improved |
| Replace the proposed schedule-network loss with the standard negative ELBO (ablation) | BDDM schedule network · LJSpeech | noise-scale prediction stability | Hurt |
| Train the schedule network after optimizing the score network | BDDM · LJSpeech | lower-bound tightness | Improved |
Closest papers by meaning
- Cauchy Diffusion: A Heavy-tailed Denoising Diffusion Probabilistic Model for Speech Synthesis (AAAI 2025 · similarity 0.90)
- DiffAR: Denoising Diffusion Autoregressive Model for Raw Speech Waveform Generation (ICLR 2024 · similarity 0.89)
- DDDM-VC: Decoupled Denoising Diffusion Models with Disentangled Representation and Prior Mixup for Verified Robust Voice Conversion (AAAI 2024 · similarity 0.89)
- DMOSpeech: Direct Metric Optimization via Distilled Diffusion Model in Zero-Shot Speech Synthesis (ICML 2025 · similarity 0.88)
- Predictive–Generative Drift Decomposition for Speech Enhancement and Separation (NeurIPS 2026 · similarity 0.88)
- Communication-Efficient Diffusion Denoising Parallelization via Reuse-then-Predict Mechanism (NeurIPS 2025 · similarity 0.87)
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.
