Research map / Image generation / Autoregressive and latent generation
DDSP: Differentiable Digital Signal Processing
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 the DDSP autoencoder instead of WaveRNN with the same conditioning | DDSP Autoencoder (Supervised) versus WaveRNN · NSynth test | Loudness (L1): 0.10 -> 0.07 | Helped |
| use the DDSP autoencoder instead of WaveRNN with the same conditioning | DDSP Autoencoder (Supervised) versus WaveRNN · NSynth test | F0 (L1): 1.00 -> 0.02 | Helped |
| use the DDSP autoencoder instead of WaveRNN with the same conditioning | DDSP Autoencoder (Supervised) versus WaveRNN · NSynth test | F0 Outliers: 0.07 -> 0.003 | Helped |
| learn F0 jointly instead of using pretrained CREPE F0 conditioning (ablation) | DDSP Autoencoder · NSynth test | F0 (L1): 0.02 -> 0.80 | Hurt |
| learn F0 jointly instead of using pretrained CREPE F0 conditioning (ablation) | DDSP Autoencoder · NSynth test | Loudness (L1): 0.07 -> 0.09 | Hurt |
| learn F0 jointly instead of using pretrained CREPE F0 conditioning (ablation) | DDSP Autoencoder · NSynth test | F0 Outliers: 0.003 -> 0.04 | Hurt |
| reduce the model to an extremely small configuration (ablation) | DDSP Autoencoder (Supervised) · Solo Violin | audio realism | Hurt |
Closest papers by meaning
- DFlow: A Generative Model Combining Denoising AutoEncoder and Normalizing Flow for High Fidelity Waveform Generation (ICML 2024 · similarity 0.87)
- MDSGen: Fast and Efficient Masked Diffusion Temporal-Aware Transformers for Open-Domain Sound Generation (ICLR 2025 · similarity 0.86)
- Contrastive Learning from Synthetic Audio Doppelgängers (ICLR 2025 · similarity 0.86)
- Fast Timing-Conditioned Latent Audio Diffusion (ICML 2024 · similarity 0.86)
- V2A-Mapper: A Lightweight Solution for Vision-to-Audio Generation by Connecting Foundation Models (AAAI 2024 · similarity 0.86)
- UniFlow-Audio: Unified Flow Matching for Audio Generation from Omni-Modalities (NeurIPS 2026 · similarity 0.85)
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.