Environmental Sound Classification with Tiny Transformers in Noisy Edge Environments
Authors:
- 14 June 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 309-314
Abstract
The unprecedented growth of edge sensor infrastructure is driving the demand function for in situ analytics, i.e. automated decision support at the point of data collection. In the present work, we detail our state-of-the-art Environmental Sound Classification (ESC) framework that is capable of near real-time acoustic categorization directly at the edge. Existing ESC algorithms primarily train and test on pristine datasets that fail in real-world deployments due their inability to handle real-world noisy environments. Methods to denoise the sounds are often computationally expensive for edge devices and do not guarantee performance improvements. To this end, we investigate a way to make existing ESC models robust and make them work in operational resource-constrained settings. Our framework employs a noisy classification model consisting of a tiny BERT-based Transformer (less than 20,000 parameters) and considers hardening of this model through the use of transmission channel noise augmentation. We detail real-world results through its deployment on a Raspberry Pi Zero and demonstrate its classification performance.Keywords
Funding Information
- Air Force Research Laboratory
This publication has 18 references indexed in Scilit:
- Noise Masking Recurrent Neural Network for Respiratory Sound Classification2018
- Deep wavelet scattering features for infrasonic threat identification2018
- A Survey on Network Methodologies for Real-Time Analytics of Massive IoT Data and Open Research IssuesIEEE Communications Surveys & Tutorials, 2017
- Deep Convolutional Neural Networks and Data Augmentation for Environmental Sound ClassificationIEEE Signal Processing Letters, 2017
- Feature extraction of some Quranic recitation using Mel-Frequency Cepstral Coeficients (MFCC)2016
- ESC2015
- Environmental sound classification with convolutional neural networks2015
- Analyzing noise robustness of MFCC and GFCC features in speaker identification2013
- Noise-Robust environmental sound classification method based on combination of ICA and MP featuresArtificial Intelligence Research, 2012
- Comparison of different implementations of MFCCJournal of Computer Science and Technology, 2001