Geometry-Conditioned Pair Representation and Covariance Reconstruction for Multi-Source Direction-of-Arrival Estimation with Microphone Arrays
Sensors · 05.11.2026 · 26 (21) · 7004
DOI: 10.3390/s26217004 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 05.11.2026. Verfasst von Zixuan Liu und 1 weiteren Autor:innen. Beteiligte Einrichtung: Detroit Green Technology Institute, Hubei University of Technology, Wuhan 430068, China. Die Arbeit nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Science and Technology Department of Hubei Province, China Scholarship Council.
Abstract (Originalsprache)
Microphone-array direction-of-arrival (DOA) estimators must cope with changes in array layout, sensor availability, and the number of active sources. We present GCPR-DOA, a geometry-conditioned pair representation that encodes each cross-spectral pair together with its microphone baseline and frequency before masked aggregation, so that one network processes arrays with 4 to 32 microphones. Two decoders use this representation: a set decoder supervised through analytic positive-semidefinite covariance reconstruction, and a spectral-moment decoder that forms a geometry-weighted steered coherence spectrum and counts sources from energy-aware features. On the LOCATA corpus, paired three-seed ablations show that geometry conditioning lowers the optimal subpattern assignment (OSPA) error by 1.35 degrees and the fixed-output angular error by 9.7 degrees. Trained on the same queries as an adapted SRP-DNN and evaluated on 46,457 common queries, the spectral-moment decoder reaches median single-source errors of 5.5–5.8 degrees, compared with 8.8–9.0 degrees, and higher active-query F1 (0.51–0.54 versus 0.47–0.49); on the three arrays other than DICIT, the two methods are comparable (5.7–5.8 versus 6.3 degrees). On the original 33,497-frame evaluation, localized F1 at ten degrees rises from 0.137 to 0.568–0.597, above all classical references.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Detroit Green Technology Institute, Hubei University of Technology, Wuhan 430068, China.
- School of Electrical and Electronic Engineering, Hubei University of Technology, Wuhan 430068, China.
- Department of Computer Science and Engineering, University of South Carolina, Columbia, SC 29201, USA.
ORCID-Profile: Wei Xiong
Förderung
- National Natural Science Foundation of China
- Science and Technology Department of Hubei Province
- China Scholarship Council
Zitieren
APA
Liu, Z., & Xiong, W. (2026). Geometry-Conditioned Pair Representation and Covariance Reconstruction for Multi-Source Direction-of-Arrival Estimation with Microphone Arrays. Sensors, 26(21), 7004. https://doi.org/10.3390/s26217004
Vancouver
Liu Z, Xiong W. Geometry-Conditioned Pair Representation and Covariance Reconstruction for Multi-Source Direction-of-Arrival Estimation with Microphone Arrays. Sensors. 2026;26(21):7004. doi:10.3390/s26217004
BibTeX
@article{Liu2026,
author = {Liu, Zixuan and Xiong, Wei},
title = {Geometry-Conditioned Pair Representation and Covariance Reconstruction for Multi-Source Direction-of-Arrival Estimation with Microphone Arrays},
journal = {Sensors},
year = {2026},
volume = {26},
number = {21},
pages = {7004},
doi = {10.3390/s26217004}
}
EUVIMED