A fine-tuned CNN (E2PANNs) deployed on a Raspberry Pi 5 detects emergency vehicle sirens in real time with adaptive frame sizing and post-processing, reporting up to 78% framewise F1 on a corrected AudioSet-Strong subset.
A safety- oriented framework for sound event detection in driving scenarios,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Real-Time Emergency Vehicle Siren Detection with Efficient CNNs on Embedded Hardware
A fine-tuned CNN (E2PANNs) deployed on a Raspberry Pi 5 detects emergency vehicle sirens in real time with adaptive frame sizing and post-processing, reporting up to 78% framewise F1 on a corrected AudioSet-Strong subset.