Detailed info

Optimizing PhiNet architectures for the detection of urban sounds on low-end devices

AuthorsAlessio Brutti, Francesco Paissan, Alberto Ancilotto, Elisabetta Farella
TitleOptimizing PhiNet architectures for the detection of urban sounds on low-end devices
AbstractSound Event Detection (SED) pipelines identify and classify relevant events in audio streams with application in the smart city domain (e.g., crowd counting, alarm triggering), thus is an asset for municipalities and law enforcement agencies. Given the large size of the areas to be monitored and the amount of data generated by the IoT sensors, large models running on centralised servers are not suitable for real-time applications. Conversely, performing SED directly on pervasive embedded devices is very attractive in terms of energy consumption, bandwidth requirements and privacy preservation. In a previous manuscript, we proposed scalable backbones from the PhiNets architectures’ family for real-time sound event detection on microcontrollers. In this paper, we extend our analysis investigating how PhiNets’ parameters scaling affects the model performance in the SED task while searching for the best configuration given the computational constraints.Experimental analysis on UrbanSound8K shows that while only the total number of parameters matters when training the model from scratch (i.e., it is independent of the scaling parameter configuration), knowledge distillation is more effective with specific scaling configurations.
ISBNΝ/Α
Conference30th European Signal Processing Conference, EUSIPCO 2022
Date29/08 – 02/09/2022
LocationBelgrade, Serbia
Year of Publication, Publisher2022
Urlhttps://doi.org/10.5281/zenodo.6641845
DOIDOI
  
  

Key Facts

  • Project Coordinator: Dr. Sotiris Ioannidis
  • Institution: Foundation for Research and Technology Hellas (FORTH)
  • E-mail: marvel-info@marvel-project.eu 
  • Start: 01.01.2021
  • Duration: 36 months
  • Participating Organisations: 17
  • Number of countries: 12

Get Connected

Funding

eu FLAG

This project has received funding from the European Union’s Horizon 2020 Research and Innovation program under grant agreement No 957337. The website reflects only the view of the author(s) and the Commission is not responsible for any use that may be made of the information it contains.