Conformal Prediction-Aware DOA Tracking
We introduce an uncertainty-aware DOA-tracking framework combining deep posterior estimation, conformal-prediction calibration, and temporal smoothing. The approach enhances stability against reverberation and burst-like directional noise, yielding more reliable trajectories and greater robustness than conventional DOA-tracking methods.
Authors
- Sharon Gannot (ORCID: https://orcid.org/0000-0002-2885-170X)
- Maya Veisman Barness
- Bracha Laufer Goldshtein
Publication Details
- Journal
- arXiv (Cornell University)
- Published
- 2026-10-29
- DOI
- https://doi.org/10.48550/arxiv.2610.39566
- Primary Topic
- Direction-of-Arrival Estimation Techniques
- Type
- preprint