Conversation Detection on Smartwatch Audio and Motion Sensing 1.0 (L+SN-LOGO)
78Macro-F1Pure-Acoustic Model + SCNNB
Evaluation results
| Method | Links | |
|---|---|---|
| Pure-Acoustic Model + SCNNBModality=Audio+Motion, Fusion=Concatenation2025.07 | 78 | |
| Pure-Acoustic Model + CNN+AttentionModality=Audio+Motion, Fusion=Concatenation2025.07 | 77.2 | |
| Pure-Acoustic ModelModality=Audio, Fusion=N/A2025.07 | 73 | |
| Pure-Acoustic Model + CNN+AttentionModality=Audio+Motion, Fusion=Softmax Averaging2025.07 | 65.2 | |
| Pure-Acoustic Model + SCNNBModality=Audio+Motion, Fusion=Softmax Averaging2025.07 | 61.4 | |
| Pure-Acoustic Model + SCNNBModality=Audio+Motion, Fusion=Self-Attention2025.07 | 57.9 | |
| Pure-Acoustic Model + CNN+AttentionModality=Audio+Motion, Fusion=Self-Attention2025.07 | 55.6 | |
| SCNNBModality=Motion, Fusion=N/A2025.07 | 53.7 | |
| CNN+AttentionModality=Motion, Fusion=N/A2025.07 | 50.8 |