Voice-Driven Semantic Perception for UAV-Assisted Emergency Networks

TL;DR

This paper introduces SIREN, an AI framework that converts emergency voice communications into structured data for UAV-assisted networks, enhancing situational awareness and network management during emergencies.

Contribution

It presents a novel integration of speech recognition and semantic extraction to enable voice-driven perception in UAV-assisted emergency networks.

Findings

Robust transcription and semantic extraction across diverse conditions

Effective identification of emergency units and locations from voice data

Main limitations include speaker diarization and geographic ambiguity

Abstract

Unmanned Aerial Vehicle (UAV)-assisted networks are increasingly foreseen as a promising approach for emergency response, providing rapid, flexible, and resilient communications in environments where terrestrial infrastructure is degraded or unavailable. In such scenarios, voice radio communications remain essential for first responders due to their robustness; however, their unstructured nature prevents direct integration with automated UAV-assisted network management. This paper proposes SIREN, an AI-driven framework that enables voice-driven perception for UAV-assisted networks. By integrating Automatic Speech Recognition (ASR) with Large Language Model (LLM)-based semantic extraction and Natural Language Processing (NLP) validation, SIREN converts emergency voice traffic into structured, machine-readable information, including responding units, location references, emergency severity, and Quality-of-Service (QoS) requirements. SIREN is evaluated using synthetic emergency scenarios with controlled variations in language, speaker count, background noise, and message complexity. The results demonstrate robust transcription and reliable semantic extraction across diverse operating conditions, while highlighting speaker diarization and geographic ambiguity as the main limiting factors. These findings establish the feasibility of voice-driven situational awareness for UAV-assisted networks and show a practical foundation for human-in-the-loop decision support and adaptive network management in emergency response operations.