Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2603.17377 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914405301616640 |
|---|---|
| author | Rozenfeld, Vadim Goldshtein, Bracha Laufer |
| author_facet | Rozenfeld, Vadim Goldshtein, Bracha Laufer |
| contents | Reliable Sound Source Localization (SSL) plays an essential role in many downstream tasks, where informed decision making depends not only on accurate localization but also on the confidence in each estimate. This need for reliability becomes even more pronounced in challenging conditions, such as reverberant environments and multi-source scenarios. However, existing SSL methods typically provide only point estimates, offering limited or no Uncertainty Quantification (UQ). We leverage the Conformal Prediction (CP) framework and its extensions for controlling general risk functions to develop two complementary UQ approaches for SSL. The first assumes that the number of active sources is known and constructs prediction regions that cover the true source locations. The second addresses the more challenging setting where the source count is unknown, first reliably estimating the number of active sources and then forming corresponding prediction regions. We evaluate the proposed methods on extensive simulations and real-world recordings across varying reverberation levels and source configurations. Results demonstrate reliable finite-sample guarantees and consistent performance for both known and unknown source-count scenarios, highlighting the practical utility of the proposed frameworks for uncertainty-aware SSL. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_17377 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Uncertainty Quantification and Risk Control for Multi-Speaker Sound Source Localization Rozenfeld, Vadim Goldshtein, Bracha Laufer Audio and Speech Processing Reliable Sound Source Localization (SSL) plays an essential role in many downstream tasks, where informed decision making depends not only on accurate localization but also on the confidence in each estimate. This need for reliability becomes even more pronounced in challenging conditions, such as reverberant environments and multi-source scenarios. However, existing SSL methods typically provide only point estimates, offering limited or no Uncertainty Quantification (UQ). We leverage the Conformal Prediction (CP) framework and its extensions for controlling general risk functions to develop two complementary UQ approaches for SSL. The first assumes that the number of active sources is known and constructs prediction regions that cover the true source locations. The second addresses the more challenging setting where the source count is unknown, first reliably estimating the number of active sources and then forming corresponding prediction regions. We evaluate the proposed methods on extensive simulations and real-world recordings across varying reverberation levels and source configurations. Results demonstrate reliable finite-sample guarantees and consistent performance for both known and unknown source-count scenarios, highlighting the practical utility of the proposed frameworks for uncertainty-aware SSL. |
| title | Uncertainty Quantification and Risk Control for Multi-Speaker Sound Source Localization |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2603.17377 |