Performance and Energy Balance: A Comprehensive Study of State-of-the-Art Sound Event Detection Systems
Francesca Ronchini1, and Romain Serizel2
1 Dipartimento di Elettronica, Informazione e Bioingegneria - Politecnico di Milano
2 Université de Lorraine, CNRS, Inria, Loria
In recent years, deep learning systems have shown a concerning trend toward increased complexity and higher energy consumption. As researchers in this domain and organizers of one of the Detection and Classification of Acoustic Scenes and Events challenges task, we recognize the importance of addressing the environmental impact of data-driven SED systems. In this paper, we propose an analysis focused on SED systems based on the challenge submissions. This includes a comparison across the past two years and a detailed analysis of this year’s SED systems. Through this research, we aim to explore how the SED systems are evolving every year in relation to their energy efficiency implications.
In order to run the jupyter notebook, you need to clone the repo, create a virtual environment and install the needed packages.
You can create the virtual environment and install the needed packages using conda with the following command:
conda create --name <env> --file requirement.txt
Once everything is installed, you can run the Jupyter Notebook following the instruction reported on it, and reproduce the results.
For more details: "Performance and energy balance: a comprehensive study of state-of-the-art sound event detection systems", Francesca Ronchini, and Romain Serizel - ICASSP 2024 - IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Seoul, Korea, Republic of, 2024,
If you use code or comments from this work, please cite our paper:
@inproceedings{ronchini2024performance,
title={Performance and energy balance: a comprehensive study of state-of-the-art sound event detection systems},
author={Ronchini, Francesca and Serizel, Romain},
booktitle={ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
pages={1096--1100},
year={2024},
organization={IEEE}
}