Detection Without Discrimination: An Edge Evaluation of Audio–Language Models for Firearm Events in Contested-Logistics Sensor Networks
Future Internet · 07.11.2026 · 18 (11) · 612
DOI: 10.3390/fi18110612 ↗Kurz gefasst
Fachartikel in der Zeitschrift Future Internet, online erschienen am 07.11.2026. Verfasst von Jyothsna Laxmi Saripalli und 6 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Acoustic sensor nodes protecting logistics sites use fixed-label classifiers, so adding a class requires new data, retraining, and redeployment of every node. Audio–language models promise to add classes by text description. We evaluated three frozen contrastive audio–language models on 25,599 events (15,241 gunshots) and on an external field set, and measured their cost on six edge platforms. On supplied clips, a vocabulary-independent score calibrated on separate data for a 5% false-positive target recalled 79% to 84% of gunshots at realized rates of 4.8% to 5.6% against unseen background sounds. On field recordings from an unseen domain, separation held on full clips (area under the ROC curve 0.95 to 0.97), but the clip-level false-positive rate rose to 7% to 11%, and only 24% to 25% of gunshots were detected end to end because the onset gate missed distant shots. Fine-grained zero-shot classification was weak: balanced accuracy was 0.53 against 0.50 for supersonic versus subsonic fire and 0.05 against 0.04 for firearm identity. A linear probe reached 0.82 at the regime level, but 0.59 with calibers held out. A firearm class added by one sentence reached 6.4% accuracy, against 54% with twenty labeled examples.
Zitieren
APA
Saripalli, J. L., Saripalli, H. H. B., Lagos, L., Gangwani, P., Soni, J., Perez-Pons, A., & Upadhyay, H. (2026). Detection Without Discrimination: An Edge Evaluation of Audio–Language Models for Firearm Events in Contested-Logistics Sensor Networks. Future Internet, 18(11), 612. https://doi.org/10.3390/fi18110612
Vancouver
Saripalli JL, Saripalli HHB, Lagos L, Gangwani P, Soni J, Perez-Pons A, et al. Detection Without Discrimination: An Edge Evaluation of Audio–Language Models for Firearm Events in Contested-Logistics Sensor Networks. Future Internet. 2026;18(11):612. doi:10.3390/fi18110612
BibTeX
@article{Saripalli2026,
author = {Saripalli, Jyothsna Laxmi and Saripalli, Hari Hara Babu and Lagos, Leonel and Gangwani, Pranav and Soni, Jayesh and Perez-Pons, Alexander and Upadhyay, Himanshu},
title = {Detection Without Discrimination: An Edge Evaluation of Audio–Language Models for Firearm Events in Contested-Logistics Sensor Networks},
journal = {Future Internet},
year = {2026},
volume = {18},
number = {11},
pages = {612},
doi = {10.3390/fi18110612}
}
EUVIMED