Shaharabany et al.

Reported on 4 benchmarks across 1 task · 1 paper · 4 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Audio4 results

Audio captioningonAudioCaps
BLEU-4· uses extra data· 2023-09-07
9.8
best: 14.3 (Audio Flamingo)
SOTA
Zero-Shot Audio Captioning via Audibility Guidance arXiv:2309.03884
Audio captioningonAudioCaps
CIDEr· uses extra data· 2023-09-07
9.2
best: 50.2 (Audio Flamingo)
SOTA
Zero-Shot Audio Captioning via Audibility Guidance arXiv:2309.03884
Audio captioningonAudioCaps
METEOR· uses extra data· 2023-09-07
8.6
best: 20.5 (Audio Flamingo)
SOTA
Zero-Shot Audio Captioning via Audibility Guidance arXiv:2309.03884
Audio captioningonAudioCaps
ROUGE-L· uses extra data· 2023-09-07
8.2
best: 40.8 (Audio Flamingo)
SOTA
Zero-Shot Audio Captioning via Audibility Guidance arXiv:2309.03884