SOURCE-LINKED INTELLIGENCE

POLARIS: Training-Free Audio Fingerprinting with Saliency-Based Landmarks and Delaunay Grouping

arXiv · AI, language, vision and robotics · article · Sep 13, 2026 · UTC

This work presents POLARIS, a training-free audio fingerprinting system that selects landmarks from a locally normalized saliency field and groups them into sparse fingerprints using Delaunay triangulation. To deal with query distortion, POLARIS adds fingerprints from two-hop Delaunay neighborhoods only at query time, without enlarging the reference index. An adaptive configuration applies this expansion only when the original fingerprints do not produce a confident match. We evaluate POLARIS on synthetic distortions from the public PEX Hard Medium benchmark, excluding queries with pitch or te

Read original source ↗ Open in workspace

recordType

paper

region

Global