Real-time On-edge Classification: an Application to Domestic Acoustic Event Recognition

In this paper two different convolutional neural network (CNN) architectures are investigated for the purpose of real-time on-edge domestic acoustic event classification. For training and evaluation of the models, a real-life acoustical dataset was recorded in 72 different home environments. A quantization-aware training scheme was applied that takes into account that the models need to run on 8-bit fixed-point processing hardware. Once trained, the models were successfully deployed on an ARM cortex-M7 microcontroller unit (i.MX RT1064). This study indicates that the used procedure can lead to an efficient and real-time embedded on-edge implementation of a domestic sound event classifier that does not sacrifice classification performance compared to its floating-point counterpart.