Binary neural network voice wake-up method and system

Abstract

The invention relates to a binary neural network voice wake-up method and system. The method comprises the following steps: acquiring a to-be-identified audio file; extracting voice features of the to-be-recognized audio file; determining an identification result of the to-be-identified audio file according to the voice features and a voice wake-up model, wherein the voice wake-up model is established through a trained binarized depth separable convolutional neural network; the specific recognition process of the voice wake-up model comprises the following steps: performing quantization processing on input by using a first convolutional layer; carrying out convolution multiplication according to the quantized voice features, the binary quantization parameter weight of a network layer and a network layer correction factor, and adding convolution data and the bias coefficient of the first convolution layer; taking the output of the first convolutional layer as the input of a second convolutional layer; and replacing the first convolutional layer with the second convolutional layer, and returning to the quantization step until an identification result is output. According to the invention, power consumption can be reduced on the basis of ensuring identification accuracy.

Description

technical field [0001] The invention relates to the field of voice wake-up, in particular to a binary neural network voice wake-up method and system. Background technique [0002] Deep learning has been proven to work well on tasks including Image Classification, Object Detection, and Natural Language Processing. A large number of applications are equipped with image (computer vision), speech related deep learning algorithms. [0003] However, the network parameters in the full-precision network are 32-bit floating-point values, which will occupy hardware space, and there are a large number of multipliers in the network, which will increase the difficulty of hardware deployment and the amount of calculation, and increase power consumption. Contents of the invention [0004] The purpose of the present invention is to provide a binary neural network voice wake-up method and system, which can reduce power consumption on the basis of ensuring recognition accuracy. [0005] T...

AI Technical Summary

Problems solved by technology

[0003] However, the network parameters in the full-precision network are 32-bit floating-point values, which will occupy hardware space, and there are a large number of multipliers in the network, which will increase the difficulty of hardware deployment and the amount of calculation, and increase power consumption.

Images