Estimated Audio-Caption Correspondences Improve Language-Based Audio Retrieval
Open paper
Benchmark
Model
Rank
Results
text-to-audio-retrieval-on-clotho
PaSST-RoBERTa & Estimated Audio–Caption Correspondences
#1
R@1: 27.69
R@5: 57.03
R@10: 70.39
mAP@10: 40.14
Rank counts only results with a code link.