Method for Reducing the Feature Space Dimension in Speech Emotion Recognition Using Convolutional Neural Networks

We consider the architectures of convolutional neural networks used to assess the emotional state of a person by their speech. The problem of increasing the efficiency of emotion recognition by reducing the computational complexity of this process is solved. To this end, we propose a method transfor...

Full description

Saved in:
Bibliographic Details
Published inAutomation and remote control Vol. 83; no. 6; pp. 857 - 868
Main Authors Iskhakova, A. O., Vol’f, D. A., Meshcheryakov, R. V.
Format Journal Article
LanguageEnglish
Published Moscow Pleiades Publishing 01.06.2022
Springer Nature B.V
Subjects
Algorithms
Artificial neural networks
CAE) and Design
Calculus of Variations and Optimal Control; Optimization
Computer-Aided Engineering (CAD
Control
Emotion recognition
Emotional factors
Emotions
Machine learning
Mathematics
Mathematics and Statistics
Mechanical Engineering
Mechatronics
Robotics
Speech recognition
Systems Theory
Thematic Issue
speech signal
detection of aggression
classification of speech signals
recognition of speech emotions
convolutional neural network
sound
socio-cyber-physical system
identification of emotional state
Online AccessGet full text

Cover

More Information
Summary:We consider the architectures of convolutional neural networks used to assess the emotional state of a person by their speech. The problem of increasing the efficiency of emotion recognition by reducing the computational complexity of this process is solved. To this end, we propose a method transforming the input data into a form suitable for machine learning algorithms.
ISSN:0005-1179
1608-3032
DOI:10.1134/S0005117922060042