ML Research Wiki / Benchmarks / Target Sound Extraction / AudioCaps

AudioCaps

Target Sound Extraction Benchmark

Performance Over Time

📊 Showing 1 results | 📏 Metric: SDRi

Top Performing Models

Rank Model Paper SDRi Date Code
1 CLAPSep CLAPSep: Leveraging Contrastive Pre-trained Model for Multi-Modal Query-Conditioned Target Sound Extraction 10.08 2024-02-27 📦 aisaka0v0/clapsep

All Papers (1)

aisaka0v0/clapsep