Text-to-Audio Retrieval on Clotho
0.212R@1WavCaps-CNN14
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| WavCaps-CNN14Year=2023, Setting=ZS2026.05 | 0.212 | — | — | — | |
| MGA-CLAPYear=2024, Setting=ZS2026.05 | 0.208 | — | — | — | |
| FLAP fusionYear=2024, Setting=ZS2026.05 | 0.203 | — | — | — | |
| CacophonyYear=2024, Setting=ZS2026.05 | 0.202 | — | — | — | |
| M2D-CLAPYear=2025, Setting=ZS2026.05 | 0.201 | — | — | — | |
| WavCaps-HTSATYear=2023, Setting=ZS2026.05 | 0.195 | — | — | — | |
| GLAPYear=2025, Setting=ZS2026.05 | 0.194 | — | — | — | |
| OmniRetriever-7BYear=2026, Setting=ZS2026.05 | 0.191 | — | — | — | |
| LAION-CLAP fusionYear=2023, Setting=ZS2026.05 | 0.182 | — | — | — | |
| PMRLSetting=Zero-shot2025.07 | 0.168 | — | 0.44 | — | |
| LanguageBindSetting=Zero-shot2025.07 | 0.167 | — | 0.52 | — | |
| MS-CLAPYear=2023, Setting=ZS2026.05 | 0.167 | — | — | — | |
| LanguageBind (CLIP-H/14)Year=2024, Setting=ZS2026.05 | 0.167 | — | — | — | |
| GRAMSetting=Zero-shot2025.07 | 0.159 | — | 0.436 | — | |
| ProposedModality=t2a, audio encoder=HTSAT-tiny, text encoder=RoBERTa-large2026.04 | 0.158 | 0.42 | 0.543 | 0.267 | |
| Microsoft-CLAPModality=t2a2026.04 | 0.156 | 0.385 | 0.51 | 0.255 | |
| LAION-CLAPModality=t2a2026.04 | 0.146 | 0.349 | 0.447 | 0.231 | |
| VASTSetting=Zero-shot2025.07 | 0.124 | — | 0.364 | — | |
| CyCLAPSsentence embedding training=unsupervised (Ls)2023.10 | 0.1208 | 0.3408 | 0.4676 | — | |
| CLAPSsentence embedding training=unsupervised (Ls)2023.10 | 0.1192 | 0.3254 | 0.4547 | — | |
| CyCLAP2023.10 | 0.119 | 0.3495 | 0.4861 | — | |
| CLAP2023.10 | 0.1167 | 0.338 | 0.471 | — | |
| MMTYear=2022, Setting=FT2026.05 | 0.067 | — | — | — | |
| Omni-Embed-NemotronYear=2025, Setting=ZS2026.05 | 0.064 | — | — | — | |
| ImageBindSetting=Zero-shot2025.07 | 0.06 | — | 0.284 | — | |
| ImageBind (ViT-H)Year=2023, Setting=ZS2026.05 | 0.06 | — | — | — | |
| Gemini Embedding 2Year=2026, Setting=ZS2026.05 | 0.052 | — | — | — | |
| AVFICSetting=Zero-shot2025.07 | 0.03 | — | 0.175 | — | |
| SGD-CLIPTime=347.48s2026.04 | 0.0278 | 0.1139 | 0.2077 | — | |
| UniConTime=13.45s2026.04 | 0.0249 | 0.111 | 0.1789 | — | |
| No alignment2026.04 | 0 | 0.0029 | 0.0096 | — |