Child emotion recognition method based on multi-attention mechanism long-short-time memory network

Abstract

The invention discloses a child emotion recognition method based on a multi-attention mechanism long-short-time memory network. the method comprises: detecting an end point of a test set speech and divides the speech into frames to extract time sequence related features, the processing algorithm of extracting temporal correlation features with different lengths based on long-short time memory network; the strategy of combining the attention mechanism with the depth of time sequence is introduced into the forgetting gate, input gate and final output of the long and short time memory network. Finally, the samples to be tested are input into the improved long-short time memory network in the training process, the emotional information can be distinguished distinctly, By introducing the depthof attention mechanism combined with timing into the forgetting gate, the output gate and the final output of the long-short time memory network, the invention not only greatly reduces the parameter quantity, but also improves the algorithm performance, increases the flexibility of the method design, and has high identification efficiency and good application prospect.

Description

technical field [0001] The invention relates to the technical field of emotion recognition, in particular to a children's emotion recognition method based on a multi-attention mechanism long-short-term memory network. Background technique [0002] Through emotion recognition, parents can better perceive children's emotions, thereby reducing the pressure on parents to take care of children, especially improving the life happiness index of young parents and improving children's quality of life. [0003] In addition, for babies who can only express their needs to their parents or guardians by crying, the emotion recognition method for them is more meaningful. Because babies have limited ways to express their emotional needs, basically they can only express their needs and moods by crying and laughing, but the information they convey may be richer, such as hunger, pain, sleepiness, etc. Faced with the above problems, the current better solution is to adopt a combination of man ...

AI Technical Summary

Problems solved by technology

[0009] The purpose of the present invention is to overcome the problems of different speech lengths and low efficiency of classification algorithms in the existing children's emotion recognition methods

Images