Your browser doesn't support javascript.
loading
Speech Emotion Recognition Based on Modified ReliefF.
Li, Guo-Min; Liu, Na; Zhang, Jun-Ao.
Afiliação
  • Li GM; College of Communication and Information Engineering, Xi'an University of Science and Technology, Xi'an 710600, China.
  • Liu N; College of Communication and Information Engineering, Xi'an University of Science and Technology, Xi'an 710600, China.
  • Zhang JA; College of Communication and Information Engineering, Xi'an University of Science and Technology, Xi'an 710600, China.
Sensors (Basel) ; 22(21)2022 Oct 25.
Article em En | MEDLINE | ID: mdl-36365853
As the key of human-computer natural interaction, the research of emotion recognition is of great significance to the development of computer intelligence. In view of the issue that the current emotional feature dimension is too high, which affects the classification performance, this paper proposes a modified ReliefF feature selection algorithm to screen out feature subsets with smaller dimensions and better performance from high-dimensional features to further improve the efficiency and accuracy of emotion recognition. In the modified algorithm, the selection range of random samples is adjusted; the correlation between features is measured by the maximum information coefficient, and the distance measurement method between samples is established based on the correlation. The experimental results on the eNTERFACE'05 and SAVEE speech emotional datasets show that the features filtered based on the modified algorithm significantly reduce the data dimensions and effectively improve the accuracy of emotion recognition.
Assuntos
Palavras-chave

Texto completo: 1 Base de dados: MEDLINE Assunto principal: Fala / Algoritmos Limite: Humans Idioma: En Ano de publicação: 2022 Tipo de documento: Article

Texto completo: 1 Base de dados: MEDLINE Assunto principal: Fala / Algoritmos Limite: Humans Idioma: En Ano de publicação: 2022 Tipo de documento: Article