Implementing deep learning on edge devices for snoring detection and reduction

This study introduces MinSnore, a novel deep learning model tailored for real-time snoring detection and reduction, specifically designed for deployment on low-configuration edge devices. By integrating MobileViTV3 blocks into the Dynamic MobileNetV3 backbone model architecture, MinSnore leverages both Convolutional Neural Networks (CNNs) and transformers to deliver enhanced feature representations with minimal computational overhead. The model was pre-trained on a diverse dataset of 46,349 audio files using the Self-Supervised Learning with Barlow Twins (SSL-BT) method, followed by fine-tuning on 17,355 segmented clips extracted from this dataset. MinSnore represents a significant breakthrough in snoring detection, achieving an accuracy of 96.37 %, precision of 96.31 %, recall of 94.12 %, and an F1-score of 95.02 %. When deployed on a single-board computer like a Raspberry Pi, the system demonstrated a reduction in snoring duration during real-world experiments. These results underscore the importance of this work in addressing sleep-related health issues through an efficient, low-cost, and highly accurate snoring mitigation solution. [Display omitted] •MinSnore, a deep learning model for real-time snoring detection, integrates MobileViTV3 blocks into a Dynamic MobileNetV3 backbone for efficient, low-configuration deployment.•Barlow Twins self-supervised learning improved MinSnore's classification, with Random Forest achieving top performance.•In real-world tests, MinSnore achieved up to a 39.05 % reduction in snoring with a specific strategy in testing with a single volunteer.