Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
A Semantically Consistent Dataset for Data-Efficient Query-Based Universal Sound Separation
Kai Li, Jintao Cheng, Chang Zeng, Zijun Yan, Helin Wang, Zixiong Su, Bo Zheng, Xiaolin Hu
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add semantic-consistency constraint to mixture construction (ablation) | AudioSep · Hive test set (175k mixtures) | SDR (dB): 3.12 -> 4.12 | Improved |
| add semantic-consistency constraint to mixture construction (ablation) | AudioSep · Hive test set (175k mixtures) | OQ: 2.96 -> 3.11 | Improved |
| add semantic-consistency constraint to mixture construction (ablation) | FlowSep · Hive test set (175k mixtures) | OQ: 2.64 -> 2.79 | Improved |
| add semantic-consistency constraint to mixture construction (ablation) | FlowSep · Hive test set (175k mixtures) | CLAP-T: 0.13 -> 0.17 | Improved |
| train AudioSep on Hive instead of original corpus | AudioSep · Hive test set (zero-shot, avg 2-5 mix) | SDR (dB): 2.37 -> 5.67 | Improved |
| train FlowSep on Hive instead of original corpus | FlowSep · Hive test set (zero-shot, avg 2-5 mix) | OQ: 2.76 -> 3.05 | Improved |
| train AudioSep on Hive (2.4k h) instead of original (14.1k h) | AudioSep · USS-Bench | SDR (dB): -1.86 -> 2.29 | Improved |
| train AudioSep on Hive (2.4k h) instead of original (14.1k h) | AudioSep · MUSDB18-HQ | SDR (dB): -1.01 -> 1.36 | Improved |
| train AudioSep on Hive instead of original corpus | AudioSep · VGGClean_eval | SDR (dB): 8.67 -> 7.61 | Hurt |
| train AudioSep on Hive instead of original corpus | AudioSep · VGGClean_eval | OQ: 3.42 -> 3.44 | Improved |
| train on Hive to reduce co-occurrence shortcut gap | AudioSep · controlled paired co-occurring vs decorrelated mixtures | SDR gap (dB): -1.41 -> -0.39 | Improved |
| train FlowSep on Hive to reduce shortcut gap | FlowSep · controlled paired co-occurring vs decorrelated mixtures | OQ gap: -0.23 -> -0.10 | Improved |
Closest papers by meaning
- Weakly-supervised Audio Separation via Bi-modal Semantic Similarity (ICLR 2024 · similarity 0.88)
- OmniSep: Unified Omni-Modality Sound Separation with Query-Mixup (ICLR 2025 · similarity 0.88)
- SSLAM: Enhancing Self-Supervised Models with Audio Mixtures for Polyphonic Soundscapes (ICLR 2025 · similarity 0.87)
- Massive Sound Embedding Benchmark (MSEB) (NeurIPS 2025 · similarity 0.85)
- DeepASA: An Object-Oriented Multi-Purpose Network for Auditory Scene Analysis (NeurIPS 2025 · similarity 0.85)
- Synthio: Augmenting Small-Scale Audio Classification Datasets with Synthetic Data (ICLR 2025 · 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.
