Research map / Detection and segmentation / CNN features
SoundDet: Polyphonic Moving Sound Event Detection and Localization from Raw Waveform
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 |
|---|---|---|---|
| treat events as complete instances using dense event proposals and joint temporal-spatial heads | SoundDet · DCASE SELD test, FOA | mAP: 0.134 -> 0.197 | Helped |
| treat events as complete instances using dense event proposals and joint temporal-spatial heads | SoundDet · DCASE SELD test, FOA | mAR: 0.256 -> 0.294 | Helped |
| add motion smoothness map (ablation) | SoundDet · DCASE SELD test, FOA | mAP: 0.117 -> 0.197 | Helped |
| add motion smoothness map (ablation) | SoundDet · DCASE SELD test, FOA | mAR: 0.247 -> 0.294 | Helped |
| add MaxCorr filter bank (ablation) | SoundDet backbone · DCASE SELD test, FOA | F20°: 0.05 -> 0.38 | Helped |
| add MaxCorr filter bank (ablation) | SoundDet backbone · DCASE SELD test, FOA | mAP: 0.025 -> 0.040 | Helped |
| add dense event proposal and temporal recovery heads to the backbone (ablation) | SoundDet · DCASE SELD test, FOA | mAP: 0.040 -> 0.197 | Helped |
| add dense event proposal and temporal recovery heads to the backbone (ablation) | SoundDet · DCASE SELD test, FOA | mAR: 0.096 -> 0.294 | Helped |
| use complete-event detection instead of framewise segment predictions | SoundDet · DCASE SELD test, FOA, All | F20°: 0.82 -> 0.81 | No clear effect |
| use raw waveform with learned MaxCorr filters rather than hand-crafted input features | SoundDet backbone · DCASE SELD test | inference time: 1.20~s -> 1.25~s | No clear effect |
Closest papers by meaning
- Action Dubber: Timing Audible Actions via Inflectional Flow (ICML 2025 · similarity 0.85)
- DiffSED: Sound Event Detection with Denoising Diffusion (AAAI 2024 · similarity 0.85)
- Learning to Visually Localize Sound Sources from Mixtures without Prior Source Knowledge (CVPR 2024 · similarity 0.84)
- Dense Audio-Visual Event Localization Under Cross-Modal Consistency and Multi-Temporal Granularity Collaboration (AAAI 2025 · similarity 0.84)
- Object-aware Sound Source Localization via Audio-Visual Scene Understanding (CVPR 2025 · similarity 0.84)
- DeepASA: An Object-Oriented Multi-Purpose Network for Auditory Scene Analysis (NeurIPS 2025 · similarity 0.84)
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.