Optimization method and system for stacked one-dimensional convolutional network wake-up acoustic model

Abstract

An embodiment of the present invention provides an optimization method for a stacked one-dimensional convolutional network wake-up acoustic model. The method includes: adjusting the expansion coefficient of the time-domain convolution layer in the stacked one-dimensional convolutional network wake-up acoustic model, increasing the receptive field output by the time-domain convolution layer; setting the activation function of the time-domain convolution layer to gate control Linear unit, using gated linear unit combined with the output of the time-domain convolutional layer to reduce the dimension of the output of the time-domain convolutional layer to optimize the stacked 1D convolutional network wake-up acoustic model. The embodiment of the present invention also provides an optimization system for a stacked one-dimensional convolutional network wake-up acoustic model. The interval of the convolution kernels in the embodiment of the present invention increases the receptive field, which effectively increases the receptive field of the model and improves the wake-up accuracy. At the same time, after the gated linear unit is combined with the S1DCNN model, the output dimension can be reduced to the original one. Half of the model parameters are better compressed, so that under the same parameter amount, a higher wake-up rate can be achieved.

Description

technical field [0001] The invention relates to the field of intelligent speech, in particular to an optimization method and system for a stacked one-dimensional convolutional network wake-up acoustic model. Background technique [0002] The S1DCNN (Stacked 1D convolutional networks, stacked one-dimensional convolutional networks) wake-up acoustic model is composed of several different S1DCNN layers; each S1DCNN layer is mainly composed of two one-dimensional convolution layers (cnn). The first convolutional layer is frequency domain convolution, the second convolutional layer is time domain convolution, and each channel is independent of each other, called depth-wise (depth) convolution. Compared with the traditional two-dimensional CNN, S1DCNN can achieve the same level of performance while reducing the amount of computation, or the performance loss is smaller, and it has higher performance in lightweight acoustic models (such as acoustic models for speech arousal). use v...

AI Technical Summary

Problems solved by technology

[0006] In order to at least solve the problem that the stacked one-dimensional convolutional network wakes up the acoustic model with a relatively single receptive field and low stability

Images