Method, apparatus and system for identifying dispersed voice emotions based on emotion dimension prediction

Abstract

The invention relates to the field of emotion computing, and in particular to a method, apparatus and system for identifying dispersed voice emotions based on emotion dimension prediction, aiming at overcoming the difficulty of current voice emotion identification methods in identifying emotions. According to the invention, the method includes the following steps: extracting the basic acoustic features of a voice, combining the basic acoustic features to form voice emotion features, performing windowing processing on the voice emotion features, after obtaining global voice emotion features, performing prediction to obtain emotion dimension information, combining the global voice emotion features and the emotion dimension information, identifying the dispersed voice emotions, and obtainingthe result from voice emotion identification. According to the invention, the method, by integrating the emotion dimension information to the global voice emotion features, increases the dimension ofthe voice emotion features, and increases the accuracy of dispersed voice emotion identification. The invention also provides an apparatus and system for identifying the dispersed voice emotions basedon emotion dimension prediction, and the apparatus and the system have the aforementioned beneficial advantages.

Description

technical field [0001] The present invention relates to the field of emotion computing, and specifically provides a discrete speech emotion recognition method, device and system based on emotion dimension prediction. Background technique [0002] With the development of artificial intelligence, the status of affective computing is becoming more and more important. Affective computing tries to endow machines with the ability to observe, understand and generate various emotions, making machines more human-like with emotions. Speech, as an important transmission medium in human communication, contains a lot of emotional information. Speech emotion recognition can improve the ability of machines to understand human voice emotions, and thus be more widely used in human-computer dialogue, making human-computer interaction more natural harmonious. [0003] Speech emotion recognition mainly includes two steps of feature extraction and classifier classification. At present, there is...

AI Technical Summary

Problems solved by technology

[0005] In order to solve the above-mentioned problems in the prior art, that is, in order to solve the problem that the recognition of the emotional state by the existing speech emotion recognition method is difficult to meet the requirements, one aspect of the present invention provides a discrete speech emotion recognition method based on emotion dimension prediction, Applied to speech emotion recognition systems, including:

Images