Audio-Text Retrieval on ParaSpeechCaps (PSC)
55.3Recall@1Contrastive-scratch (Ours)
Evaluation Results
| Method | Links | |
|---|---|---|
| Contrastive-scratch (Ours)Label=Caption*, Evaluation Protocol=audio-language alignment2026.03 | 55.3 | |
| Contrastive-scratchLabel=Caption, Evaluation Protocol=audio-language alignment2026.03 | 55 | |
| Captioning-scratch (Ours)Label=Caption*, Evaluation Protocol=audio-language alignment2026.03 | 50.2 | |
| PAR (Ours-UTS)Label=Tag Sequence*, Evaluation Protocol=audio-language alignment2026.03 | 49.8 | |
| MTC (Ours-UTS)Label=Tag*, Evaluation Protocol=audio-language alignment2026.03 | 49.6 | |
| MTC (AudioSet)Label=Tag, Evaluation Protocol=audio-language alignment2026.03 | 49.2 | |
| Captioning-scratchLabel=Caption, Evaluation Protocol=audio-language alignment2026.03 | 49.2 | |
| Multi-Task (Ours)Label=Tag*, Caption*, Evaluation Protocol=audio-language alignment2026.03 | 49 |