Sparsity Through Spiking Convolutional Neural Network for Audio Classification at the Edge

Sparsity Through Spiking Convolutional Neural Network for Audio Classification at the Edge

2023 IEEE International Symposium on Circuits and Systems (ISCAS)

10.1109/ISCAS46773.2023.10181974

http://dx.doi.org/10.1109/iscas46773.2023.10181974

Cong Sheng Leow, Wang Ling Goh, Yuan Gao

21 July 2023

Leow, C. S., Goh, W. L., & Gao, Y. (2023, May 21). Sparsity Through Spiking Convolutional Neural Network for Audio Classification at the Edge. 2023 IEEE International Symposium on Circuits and Systems (ISCAS). https://doi.org/10.1109/iscas46773.2023.10181974

Convolutional neural networks (CNNs) have shown to be effective for audio classification. However, deep CNNs can be computationally heavy and unsuitable for edge intelligence as embedded devices are generally constrained by memory and energy requirements. Spiking neural networks (SNNs) offer potential as energy-efficient networks but typically underperform typical deep neural networks in accuracy. This paper proposes a spiking convolutional neural network (SCNN) that exhibits excellent accuracy of above 98 % on a multi-class audio classification task. Accuracy remains high with weight quantization to INT8-precision. Additionally, this paper examines the role of neuron parameters in co-optimizing activation sparsity and accuracy.

Publisher Copyright

This research / project is supported by the A*STAR - Cyber-Physiochemical Interface programme
Grant Reference no. : A18A1b0045

© 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

https://oar.a-star.edu.sg/communities-collections/articles/20274

2158-1525

Institute of Microelectronics