Sound Classification on Vocal Imitation
0.295ScoreEnsemble (Submission)
Evaluation results
| Method | Links | |
|---|---|---|
| Ensemble (Submission)Ensemble Strategy=Embedding Concatenation2026.01 | 0.295 | |
| Dasheng 1.2BParameter Count=1.2B2026.01 | 0.293 | |
| Challenge BaselineDescription=Best among Dasheng-base, data2vec, and Whisper2026.01 | 0.238 | |
| BEATs (300M) SpeechParameter Count=300M, Pre-training Mixture=Speech-heavy (70:15:15)2026.01 | 0.223 | |
| BEATs (300M) BalancedParameter Count=300M, Pre-training Mixture=Balanced (40:30:30)2026.01 | 0.214 | |
| BEATs (90M) iter3Parameter Count=90M, Iteration=32026.01 | 0.212 |