Neuromorphic Speech Recognition With Photonic Convolutional Spiking Neural Networks
Shuiying Xiang, Tianrui Zhang, Yanan Han, Xingxing Guo, Yahui Zhang, Yuechun Shi, Yue Hao
Abstract
Spiking neural network (SNN) have attracted lots of attention due to its event-driven nature and powerful computation capability. However, it is still limited to simple task due to the training difficulty. In this work, we propose a hybrid architecture of photonic convolutional spiking neural network (PCSNN) to realize the speech recognition task. In the PCSNN, the feature extraction is realized by a convolution SNN with unsupervised learning algorithm, the classification is realized by a photonic SNN with modified time-based supervised training algorithm. The TIDIGITS dataset is used to test the speech recognition performance of the proposed PCSNN, and the highest testing accuracy is 93.75%. The proposed PCSNN provides a solution for architecture and algorithm co-design for the speech recognition task, which is helpful for extending the applications of photonic SNN.