# Listening for Sirens: Locating and Classifying Acoustic Alarms in City Scenes

arXiv: https://arxiv.org/abs/1810.04989 · HTML: https://mlsanity.com/paper/1810.04989/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Oct 2018.

## Built on by (most cited first, 6 of 6)

- [Binaural SoundNet: Predicting Semantics, Depth and Motion with Binaural Sounds](https://mlsanity.com/paper/2109.02763/) (2021)
- [From Large-scale Audio Tagging to Real-Time Explainable Emergency Vehicle Sirens Detection](https://mlsanity.com/paper/2506.23437/) (2025)
- [Improving the Environmental Perception of Autonomous Vehicles using Deep Learning-based Audio Classification](https://mlsanity.com/paper/2209.04075/) (2022)
- [Sound event localization and classification using WASN in Outdoor Environment](https://mlsanity.com/paper/2403.20130/) (2024)
- [Multitask frame-level learning for few-shot sound event detection](https://mlsanity.com/paper/2403.11091/) (2024)
- [Predictive audio representations for early detection and tracking of hidden dynamic objects](https://mlsanity.com/paper/2609.13595/) (2026)

## Abstract (arXiv)

This paper is about alerting acoustic event detection and sound source localisation in an urban scenario. Specifically, we are interested in spotting the presence of horns, and sirens of emergency vehicles. In order to obtain a reliable system able to operate robustly despite the presence of traffic noise, which can be copious, unstructured and unpredictable, we propose to treat the spectrograms of incoming stereo signals as images, and apply semantic segmentation, based on a Unet architecture, to extract the target sound from the background noise. In a multi-task learning scheme, together with signal denoising, we perform acoustic event classification to identify the nature of the alerting sound. Lastly, we use the denoised signals to localise the acoustic source on the horizon plane, by regressing the direction of arrival of the sound through a CNN architecture. Our experimental evaluation shows an average classification rate of 94%, and a median absolute error on the localisation of 7.5deg when operating on audio frames of 0.5s, and of 2.5deg when operating on frames of 2.5s. The system offers excellent performance in particularly challenging scenarios, where the noise level is remarkably high.