Audio captioning on AudioCaps
Metric: FENSE (higher is better)
Metric: FENSE (higher is better)
| # | Model↕ | FENSE▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | SLAM-AAC | 0.668 | Yes | SLAM-AAC: Enhancing Audio Captioning with Paraph... | 2024-10-12 | Code |
| 2 | EnCLAP++-large | 0.665 | Yes | EnCLAP++: Analyzing the EnCLAP Framework for Opt... | 2024-09-02 | Code |
| 3 | LOAE | 0.664 | Yes | Enhancing Automated Audio Captioning via Large L... | 2024-06-19 | Code |
| 4 | EnCLAP++-base | 0.661 | Yes | EnCLAP++: Analyzing the EnCLAP Framework for Opt... | 2024-09-02 | Code |
| 5 | CNext-trans | 0.6431 | No | - | - | - |