Title :
Emotion recognition using Lyapunov exponent of the Mel-frequency energy bands
Author :
Feraru, Monica ; Zbancioc, Marius
Author_Institution :
Inst. of Comput. Sci., Iaşi, Romania
Abstract :
This paper presents a method for emotion recognition by using LLE - Largest Lyapunov exponent of the Mel-frequency energy bands for the Romanian language. The emotion recognition for features vectors that contains LLE is better using Support Vector Machine - SVM classifier (76.4%) than Weighted K-Nearest Neighbors - WKNN classifier (72.8%). The most efficient combination was LLE with LPC - linear predictive coefficients, respectively with PARCOR - partial correlation coefficients. The best emotion recognized by using WKNN classifier is the joy state (70-80%) and the least recognized is neutral tone.
Keywords :
emotion recognition; natural language processing; signal classification; support vector machines; LLE; LPC; Lyapunov exponent; Mel-frequency energy bands; PARCOR; Romanian language; SVM classifier; WKNN classifier; emotion recognition; features vectors; linear predictive coefficients; partial correlation coefficients; support vector machine; Band-pass filters; Emotion recognition; Feature extraction; Mel frequency cepstral coefficient; Nonlinear dynamical systems; Support vector machine classification; Mel-frequency; automatic emotion recognition; largest Lyapunov exponent;
Conference_Titel :
Electronics, Computers and Artificial Intelligence (ECAI), 2014 6th International Conference on
Print_ISBN :
978-1-4799-5478-0
DOI :
10.1109/ECAI.2014.7090140
