Conversation Detection on Smartwatch Audio and Motion Sensing SN 1.0
68.1Macro F1Pure-Acoustic Model + CNN+Attention
Evaluation results
| Method | Links | |
|---|---|---|
| Pure-Acoustic Model + CNN+AttentionModality=Audio+Motion, Fusion=Concatenation2025.07 | 68.1 | |
| Pure-Acoustic Model + SCNNBModality=Audio+Motion, Fusion=Concatenation2025.07 | 67.5 | |
| Pure-Acoustic ModelModality=Audio, Fusion=N/A2025.07 | 64.9 | |
| Pure-Acoustic Model + SCNNBModality=Audio+Motion, Fusion=Self-Attention2025.07 | 62.8 | |
| Pure-Acoustic Model + CNN+AttentionModality=Audio+Motion, Fusion=Self-Attention2025.07 | 55.8 | |
| Pure-Acoustic Model + SCNNBModality=Audio+Motion, Fusion=Softmax Averaging2025.07 | 55.2 | |
| Pure-Acoustic Model + CNN+AttentionModality=Audio+Motion, Fusion=Softmax Averaging2025.07 | 50.7 | |
| SCNNBModality=Motion, Fusion=N/A2025.07 | 49 | |
| CNN+AttentionModality=Motion, Fusion=N/A2025.07 | 48.7 |