Real-Time Sound Event Localization and Detection: Deployment Challenges on Edge Devices
Abstract
Sound event localization and detection (SELD) is critical for various real-world applications, including smart monitoring and Internet of Things (IoT) systems. Although deep neural networks (DNNs) represent the state-of-the-art approach for SELD, their significant computational complexity and model sizes present challenges for deployment on resource-constrained edge devices, especially under real-time conditions. Despite the growing need for real-time SELD, research in this area remains limited. In this paper, we investigate the unique challenges of deploying SELD systems for real-world, real-time applications by performing extensive experiments on a commercially available Raspberry Pi 3 edge device. Our findings reveal two critical, often overlooked considerations: the high computational cost of feature extraction and the performance degradation associated with low-latency, real-time inference. This paper provides valuable insights and considerations for future work toward developing more efficient and robust real-time SELD systems
Keywords
Cite
@article{arxiv.2409.11700,
title = {Real-Time Sound Event Localization and Detection: Deployment Challenges on Edge Devices},
author = {Jun Wei Yeow and Ee-Leng Tan and Jisheng Bai and Santi Peksi and Woon-Seng Gan},
journal= {arXiv preprint arXiv:2409.11700},
year = {2024}
}
Comments
Submitted to ICASSP'25. Code is available at this link : https://github.com/itsjunwei/Realtime-SELD-Edge