Patent · US Active

Method for emotion recognition based on minimum classification error

US8180638B2 · kind B2 · utility

7Cited by
2References
6Claims
0Family size

Assignee

Inventors

Key dates

Filing dateFeb 23, 2010
Grant dateMay 15, 2012
Priority date
Expiry dateSep 2, 2030

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG10L17/26
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Disclosed herein is a method for emotion recognition based on a minimum classification error. In the method, a speaker's neutral emotion is extracted using a Gaussian mixture model (GMM), other emotions except the neutral emotion are classified using the Gaussian Mixture Model to which a discriminative weight for minimizing the loss function of a classification error for the feature vector for emotion recognition is applied. In the emotion recognition, the emotion recognition is performed by applying a discriminative weight evaluated using the Gaussian Mixture Model based on minimum classification error to feature vectors of the emotion classified with difficult, thereby enhancing the performance of emotion recognition.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.