Speech classification model training method and device, equipment and storage medium

Abstract

The invention relates to the field of artificial intelligence, and particularly discloses a voice classification model training method and device, equipment and a storage medium, and the method comprises the steps: obtaining sample data which comprises a sample voice and a sample label corresponding to the sample voice; preprocessing the sample voice to obtain a vector matrix corresponding to the sample voice; inputting the vector matrix into a variational information bottleneck processing network of an initial voice classification model to obtain sentence representation corresponding to the sample voice; and inputting the sentence representation into a classification network of the initial voice classification model to obtain a prediction label, and then performing iterative training on the initial voice classification model according to the sample label and the prediction label to obtain a trained voice classification model. A variational information bottleneck processing network is added into a voice classification model, so that sample information is compressed, useless information is inhibited, and an over-fitting phenomenon is reduced.

Description

technical field [0001] The present application relates to the field of artificial intelligence, in particular to a training method, device, equipment and storage medium for a speech classification model. Background technique [0002] At present, many deep learning networks (Deep Neural Networks, DNN) headed by Convolutional Neural Networks (CNN) are widely used in various downstream tasks, such as speech classification tasks. In speech classification tasks, a simple CNN can often achieve good classification results. Most CNN networks mark the voice during training, and establish a connection between the voice information and the target label to train the CNN model. However, this training method is limited by the accuracy of the label, the amount of sample data, and the distribution of samples. In this case, the labeling cost is high and overfitting is prone to occur. Contents of the invention [0003] The present application provides a training method, device, equipment ...

AI Technical Summary

Problems solved by technology

Most CNN networks mark the voice during training, and establish a connection between the voice information and the target label to train the CNN model. However, this training method is limited by the accuracy of the label, the amount of sample data, and the distribution of samples. In this case, the cost of labeling is high, and it is prone to overfitting

Images