Universiti Teknologi Malaysia Institutional Repository

MFCC global features selection in improving speech emotion recognition rate

Zaidan, Noor Aina and Salam, Md. Sah (2015) MFCC global features selection in improving speech emotion recognition rate. In: International Conference on Machine Learning and Signal Processing MALSIP 2015, 15-17 Dec, 2015, Melaka, Malaysia.

Full text not available from this repository.

Official URL: http://cds.cern.ch/record/2196665?ln=en

Abstract

Feature selection is one of the important aspects that contribute most to the emotion recognition system performance as well as the database and the classification technique used. Based on the previous finding, MFCC features is said to be good for emotion recognition purpose. This paper discusses the use of MFCC features to recognize human emotion on Berlin database in the German language. Global features are extracted from MFCC and tested with three classification methods in recognizing emotions; Naive Bayes, Artificial Neural Network (ANN) and Support Vector Machine (SVM). Initial result from the experiment is quite good and will be further discussed in this paper.

Item Type:Conference or Workshop Item (Paper)
Uncontrolled Keywords:speech emotion recognition, MFCC
Subjects:B Philosophy. Psychology. Religion > BF Psychology
Divisions:Islamic Civilisation
ID Code:61330
Deposited By: Widya Wahid
Deposited On:31 Mar 2017 14:41
Last Modified:20 Aug 2017 15:06

Repository Staff Only: item control page