Korea Institute of Science and Technology

Kye Hwan Lee

Ig Jae Kim

Joon-Hyuk Chang

Chang Seok Bae

Hyoung Gon Kim

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.

Growing community of inventors

Gwangmyeong-si, South Korea

Kye Hwan Lee