ML Research Wiki / Benchmarks / Sound Event Detection / DESED

DESED

Sound Event Detection Benchmark

Performance Over Time

📊 Showing 10 results | 📏 Metric: event-based F1 score

Top Performing Models

Rank Model Paper event-based F1 score Date Code
1 HTS-AT HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection 50.70 2022-02-02 📦 retrocirce/hts-audio-transformer
2 MAT-SED 📚 MAT-SED: A Masked Audio Transformer with Masked-Reconstruction Based Pre-training for Sound Event Detection 0.59 2024-08-16 📦 cai525/transformer4sed
3 JiTTER 📚 JiTTER: Jigsaw Temporal Transformer for Event Reconstruction for Self-Supervised Sound Event Detection 0.58 2025-02-28 📦 frednam93/JiTTER-SED
4 ATST-SED 📚 Fine-tune the pretrained ATST model for sound event detection 0.58 2023-09-15 📦 Audio-WestlakeU/ATST-SED
5 ABC + MDFD-CRNN 📚 Pushing the Limit of Sound Event Detection with Multi-Dilated Frequency Dynamic Convolution 0.58 2024-06-19 📦 frednam93/MDFD-SED
6 MDFD-CRNN Pushing the Limit of Sound Event Detection with Multi-Dilated Frequency Dynamic Convolution 0.49 2024-06-19 📦 frednam93/MDFD-SED
7 SE-CRNN-16 with DualKD 📚 Dual Knowledge Distillation for Efficient Sound Event Detection 0.47 2024-02-05 -
8 FDY-CRNN Frequency Dynamic Convolution: Frequency-Adaptive Pattern Recognition for Sound Event Detection 0.45 2022-03-29 📦 frednam93/FDY-SED
9 RCT RCT: Random Consistency Training for Semi-supervised Sound Event Detection 0.44 2021-10-21 📦 Audio-WestlakeU/RCT-Random-Consistency-Training 📦 audio-westlakeu/rct
10 FiltAug SED Heavily Augmented Sound Event Detection utilizing Weak Predictions 0.43 2021-07-08 📦 frednam93/FilterAugSED

All Papers (10)

retrocirce/hts-audio-transformer
cai525/transformer4sed
frednam93/JiTTER-SED
Audio-WestlakeU/ATST-SED
frednam93/MDFD-SED
frednam93/MDFD-SED
frednam93/FDY-SED
Audio-WestlakeU/RCT-Random-Consistency-Training audio-westlakeu/rct
frednam93/FilterAugSED