Speech emotion recognition method

Abstract

The invention discloses a speech emotion recognition method. The method includes the steps that firstly, a speech signal is converted into a spectrogram to serve as initial input; secondly, a deep convolutional neural network is trained to automatically extract emotion features; thirdly, a stack type auto-encoder is trained for each kind of emotions, and all the stack type auto-encoders are fused to automatically construct membership functions of an emotion fuzzy set; fourthly, the features obtained in the second step are subjected to feature optimization by means of the fuzzy optimal theory in the third step; fifthly, emotion classification recognition is conducted by means of a Softmax classifier. The method takes abstract fuzzy properties of speech emotion information into consideration, the extracted emotion features are subjected to selective fuzzy optimization to improve the significance of the features, fuzzy membership functions in the fuzzy theory are automatically constructed by means of the concept of deep neural network layer-by-layer training, and the problem that the proper membership functions in the fuzzy theory are difficult to select and determine is solved.

Description

technical field [0001] The invention relates to the technical field of speech emotion recognition, in particular to a speech emotion recognition method based on a deep neural network model and feature fuzzy optimization. Background technique [0002] Human beings can express emotions through many signals, such as heartbeat frequency, voice, face, behavior, etc. Computers can identify and obtain human emotional states by analyzing one or more of these signals, among which speech is the most important and convenient way of communication in daily life. With the rapid development of the field of computer multimedia information processing technology and the field of artificial intelligence, various research institutions pay more and more attention to how to make computers recognize human voice emotions. [0003] Emotion recognition of speech belongs to the field of pattern recognition, but it is slightly different. For example, for ordinary image recognition, many small animals...

AI Technical Summary

Problems solved by technology

However, there is a shortcoming that only using these deep neural network models to extract features and then perform classification and recognition does not fully consider and utilize the fuzzy characteristics of speech emotional information, which is quite important in speech emotional features.

Images