Abstract
It is a well-established practice to build a robust system for sound event detection by training supervised deep learning models on large datasets, but audio data collection and labeling are often challenging and require large amounts of effort. This paper proposes a workflow based on few-shot metric learning for emergency siren detection performed in steps: prototypical networks are trained on publicly available sources or synthetic data in multiple combinations, and at inference time, the best knowledge learned in associating a sound with its class representation is transferred to identify ambulance sirens, given only a few instances for the prototype computation. Performance is evaluated on siren recordings acquired by sensors inside and outside the cabin of an equipped car, investigating the contribution of filtering techniques for background noise reduction. The results show the effectiveness of the proposed approach, achieving AUPRC scores equal to 0.86 and 0.91 in unfiltered and filtered conditions, respectively, outperforming a convolutional baseline model with and without fine-tuning for domain adaptation. Extensive experiments conducted on several recording sensor placements prove that few-shot learning is a reliable technique even in real-world scenarios and gives valuable insights for developing an in-car emergency vehicle detection system.
Subject
Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry
Reference69 articles.
1. Emergency Vehicle Detection System;Brill;U.S. Patent,2002
2. Systems and Methods for Assessing Sound within a Vehicle Using Machine Learning Techniques;Sanchez;U.S. Patent,2019
3. Vehicle Acoustic-Based Emergency Vehicle Detection;Seifert;U.S. Patent,2022
4. Listening for Sirens: Locating and Classifying Acoustic Alarms in City Scenes
5. Emergency signal classification for the hearing impaired using multi-channel convolutional neural network architecture;Padhy;Proceedings of the 2019 IEEE Conference on Information and Communication Technology,2019
Cited by
4 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献