Compact recurrent neural networks for acoustic event detection on low-energy low-complexity platforms

Abstract

Outdoor acoustic events detection is an exciting research field but challenged by the need for complex algorithms and deep learning techniques, typically requiring many computational, memory, and energy resources. This challenge discourages IoT implementation, where an efficient use of resources is required. However, current embedded technologies and microcontrollers have increased their capabilities without penalizing energy efficiency. This paper addresses the application of sound event detection at the edge, by optimizing deep learning techniques on resource-constrained embedded platforms for the IoT. The contribution is two-fold: firstly, a two-stage student-teacher approach is presented to make state-of-the-art neural networks for sound event detection fit on current microcontrollers; secondly, we test our approach on an ARM Cortex M4, particularly focusing on issues related to 8-bits quantization. Our embedded implementation can achieve 68% accuracy in recognition on Urbansound8k, not far from state-of-the-art performance, with an inference time of 125 ms for each second of the audio stream, and power consumption of 5.5 mW in just 34.3 kB of RAM.

References in corpus (13)

• Distilling the Knowledge in a Neural Network
• FitNets: Hints for Thin Deep Nets
• BinaryConnect: Training Deep Neural Networks with binary weights during propagations
• Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation
• Deep Convolutional Neural Networks and Data Augmentation for Environmental Sound Classification
• An Analysis of Deep Neural Network Models for Practical Applications
• Predicting Parameters in Deep Learning
• Fixed Point Quantization of Deep Convolutional Networks
• Hello Edge: Keyword Spotting on Microcontrollers
• An IoT Endpoint System-on-Chip for Secure and Energy-Efficient Near-Sensor Analytics
• Extremely Low Bit Neural Network: Squeeze the Last Bit Out with ADMM
• In Teacher We Trust: Learning Compressed Models for Pedestrian Detection
• Deep Residual Learning for Small-Footprint Keyword Spotting

Cited by in corpus (2)

• Sound Event Detection with Binary Neural Networks on Tightly Power-Constrained IoT Devices
• TinyML for Acoustic Anomaly Detection in IoT Sensor Networks