Training method of emotion recognition model, emotion recognition method, device, equipment, and storage medium

Abstract

The application relates to the field of intelligent decision making. An emotion recognition model is trained based on deep learning. The invention particularly discloses a training method of the emotion recognition model, an emotion recognition method, an emotion recognition device, equipment, and a storage medium. The method comprises the following steps: acquiring voice information of a user anda corresponding data tag; constructing sample data according to the voice information and the corresponding data tag; performing pre-processing on the voice information in the sample data to obtain acorresponding frequency spectrum vector according to a pre-processing rule; extracting a pre-set recurrent neural network, wherein the recurrent neural network comprises an attention mechanism, and the attention mechanism is used for enhancing part area in the voice information; based on the recurrent neural network, performing model training to obtain the emotion recognition model according to the frequency spectrum vector corresponding to the voice information and the data tag. According to the method, the generalization of the emotion recognition model can be improved, and the accuracy ofmodel recognition can be improved.

Description

technical field [0001] The present application relates to the technical field of model training, and in particular to an emotion recognition model training method, emotion recognition method, device, computer equipment and storage medium. Background technique [0002] In recent years, the emotion recognition model based on machine learning that uses voice to recognize user emotions has been widely developed, but the emotion recognition for voice still faces many challenges. For example, in order to generate continuous and accurate recognition of positive and negative emotions, some recognition models use The combination of text and acoustic features requires the use of Automatic Speech Recognition (ASR) technology to convert sound into text information, but there is a serious delay problem. At the same time, the emotion recognition model also has the problem of poor generalization. When the model is applied to a new speaker, its accuracy will decrease. Contents of the inve...

AI Technical Summary

Problems solved by technology

[0002] In recent years, the emotion recognition model based on machine learning that uses voice to recognize user emotions has been widely developed, but the emotion recognition for voice still faces many challenges. For example, in order to generate continuous and accurate recognition of positive and negative emotions, some recognition models use Th

Images