📊 Showing 5 results | 📏 Metric: EmoA
| Rank | Model | Paper | EmoA | Date | Code |
|---|---|---|---|---|---|
| 1 | M2D-CLAP | M2D2: Exploring General-purpose Audio-Language Representations Beyond CLAP | 77.40 | 2025-03-28 | 📦 nttcslab/m2d 📦 nttcslab/eval-audio-repr |
| 2 | M2D2 | M2D2: Exploring General-purpose Audio-Language Representations Beyond CLAP | 76.70 | 2025-03-28 | 📦 nttcslab/m2d 📦 nttcslab/eval-audio-repr |
| 3 | M2D | M2D2: Exploring General-purpose Audio-Language Representations Beyond CLAP | 76.10 | 2025-03-28 | 📦 nttcslab/m2d 📦 nttcslab/eval-audio-repr |
| 4 | Jukebox (Pre-training: CALM) | Codified audio language modeling learns useful representations for music information retrieval | 72.10 | 2021-07-12 | 📦 p-lambda/jukemir |
| 5 | CLMR (Pre-training: contrastive) | Codified audio language modeling learns useful representations for music information retrieval | 67.80 | 2021-07-12 | 📦 p-lambda/jukemir |