| Paper | Code | METEOR | BLEU-4 | CIDEr | ROUGE-L | SPICE | SPIDEr | ModelName | ReleaseDate |
|---|---|---|---|---|---|---|---|---|---|
| Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities | ✓ Link | 20.5 | 14.3 | 50.2 | 40.8 | 15.1 | 32.6 | Audio Flamingo | 2024-02-02 |
| Zero-shot audio captioning with audio-language model guidance and audio context keywords | ✓ Link | 12.3 | 6.8 | 28.1 | 33.1 | 8.6 | 18.3 | ZerAuCap | 2023-11-14 |
| Zero-Shot Audio Captioning via Audibility Guidance | 8.6 | 9.8 | 9.2 | 8.2 | Shaharabany et al. | 2023-09-07 | |||
| Zero-shot audio captioning with audio-language model guidance and audio context keywords | ✓ Link | 4.1 | 0 | 0.1 | 17.8 | 0 | 0 | No audio (baseline) | 2023-11-14 |