TinyML for Acoustic Anomaly Detection in IoT Sensor Networks

TL;DR

This paper introduces a TinyML pipeline for real-time acoustic anomaly detection on IoT edge devices, utilizing Mel Frequency Cepstral Coefficients and a lightweight neural network, achieving 91% accuracy.

Contribution

The work presents a novel, energy-efficient TinyML approach for environmental sound anomaly detection directly on microcontrollers in IoT networks.

Findings

Achieved 91% test accuracy on UrbanSound8K dataset.

Demonstrated reliable anomaly detection with balanced F1-scores of 0.91.

Validated the feasibility of embedded acoustic monitoring in IoT systems.

Abstract

Tiny Machine Learning enables real-time, energy-efficient data processing directly on microcontrollers, making it ideal for Internet of Things sensor networks. This paper presents a compact TinyML pipeline for detecting anomalies in environmental sound within IoT sensor networks. Acoustic monitoring in IoT systems can enhance safety and context awareness, yet cloud-based processing introduces challenges related to latency, power usage, and privacy. Our pipeline addresses these issues by extracting Mel Frequency Cepstral Coefficients from sound signals and training a lightweight neural network classifier optimized for deployment on edge devices. The model was trained and evaluated using the UrbanSound8K dataset, achieving a test accuracy of 91% and balanced F1-scores of 0.91 across both normal and anomalous sound classes. These results demonstrate the feasibility and reliability of embedded acoustic anomaly detection for scalable and responsive IoT deployments.