Research map / Vision-language and multimodal / Cross-modal learning
Audio-Visual Speaker Diarization Based on Spatiotemporal Bayesian Fusion
Israel D. Gebru, Silèye Ba, Xiaofei Li, Radu Horaud
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use the proposed audio-visual association instead of TREM localization (ablation) | proposed method · AVDIAR | DER (%): 48.72 -> 15.32 | Improved |
| use the proposed association instead of GCC-PHAT localization (ablation) | proposed method · AVDIAR | DER (%): 58.87 -> 15.32 | Improved |
| use the proposed association instead of TREM (ablation) | proposed method · AVASM | DER (%): 33.89 -> 7.58 | Improved |
| use TREM rather than GCC-PHAT for localization (ablation) | proposed method · MVAD | DER (%): 28.45 -> 6.57 | Improved |
| use TREM rather than GCC-PHAT for localization (ablation) | proposed method · AV16P3 | DER (%): 22.82 -> 8.02 | Improved |
| use TREM rather than GCC-PHAT multi-source localization (ablation) | proposed method · AVDIAR | DER (%): 58.87 -> 48.72 | Improved |
| use proposed method instead of Gebru et al. active speaker tracking | Gebru et al. · AV16P3 | DER (%): 20.04 -> 8.02 | Improved |
| use proposed method instead of Gebru et al. | Gebru et al. · AVDIAR | DER (%): 27.78 -> 15.32 | Improved |
| use proposed method instead of DiarTK (audio only) | DiarTK · MVAD | DER (%): 29.33 -> 6.57 | Improved |
| use proposed with TREM instead of Minotto et al. | Minotto et al. · MVAD | DER (%): 11.18 -> 6.57 | Improved |
| use proposed method instead of Gebru et al. with single speaker | Gebru et al. · AV16P3 seq15-1p-0111 | DER (%): 3.29 -> 3.29 | No clear effect |
Closest papers by meaning
- Variational Bayesian Inference for Audio-Visual Tracking of Multiple Speakers (TPAMI 2019 · similarity 0.89)
- Robust Audio-Visual Segmentation via Audio-Guided Visual Convergent Alignment (CVPR 2025 · similarity 0.84)
- Seeing Speech and Sound: Distinguishing and Locating Audio Sources in Visual Scenes (CVPR 2025 · similarity 0.84)
- Unveiling the Power of Audio-Visual Early Fusion Transformers with Dense Interactions through Masked Modeling (CVPR 2024 · similarity 0.84)
- Dense Audio-Visual Event Localization Under Cross-Modal Consistency and Multi-Temporal Granularity Collaboration (AAAI 2025 · similarity 0.84)
- Learning Spatial Features from Audio-Visual Correspondence in Egocentric Videos (CVPR 2024 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
