Old people speech emotion identification method based on predication-based multi-feature fusion

Abstract

The invention discloses an old people speech emotion identification method based on predication-based multi-feature fusion. The method comprises the following steps: obtaining a speech emotion database of an empty nester; extracting three different characteristic parameters from each piece of speech and expression in the database respectively; fusing the multiple features through a prediction-based method; carrying out feature identification through an SVM; and outputting emotion class having the highest accuracy predicated under the same section of speech and obtaining an identification result. A prediction-based fusion framework comprises two parts: a cross-feature prediction assembly, which is used for fusing the three features by modeling relationship between the multiple features, connection of the three features being replaced by a first group of predictors, which learn mapping relation between the three characteristic parameters of speech emotion categories respectively; and an in-feature prediction assembly, which is used for carrying out modeling on time evolution of the three features, the in-feature prediction assembly being corresponding to decision-level fusion, and each feature being modeled by two second group predictors, which learn mapping relation between past and current features of each category.

Description

technical field [0001] The invention belongs to the field of signal processing and pattern recognition, and more specifically relates to a voice emotion recognition method for the elderly based on prediction and multi-feature fusion. Background technique [0002] In recent decades, human-computer interaction technology has developed rapidly, but with the continuous emergence of various intelligent machines, people have begun to pay attention to this question: whether to let computers perceive emotions. As we all know, people will have ups and downs of emotions such as joy, anger, sorrow, and joy anytime and anywhere. When people make decisions or deal with things, too many emotional factors will lead to negative results. unattainable. But can a machine without emotion, unable to perceive emotion, play by ear? [0003] The term "affective computing" was first proposed by Professor Picard of the Massachusetts Institute of Technology in the book "Affective Computing" publishe...

AI Technical Summary

Problems solved by technology

[0005] In the prior art, when humans and computers communicate emotionally, it is impossible to guarantee that the accuracy of each emotion recognition rate has a high percentage, and various algorithms have obvious differences in the ability to express and distinguish different emotional feature vectors ;Speech recognition system has a strong dependence on environmental conditions and poor adaptability; it is easy to cause pronunciation distortion when used in a noisy environment; more than half of the recognition errors come from the endpoint detector; the selection of speech recognition primitives is not appropriate

Images