Universiti Teknologi Malaysia Institutional Repository

Speech emotion classification using SVM and MLP on prosodic and voice quality features

Idris, Inshirah and Salam, Md. Sah and Sunar, Mohd. Shahrizal (2016) Speech emotion classification using SVM and MLP on prosodic and voice quality features. Jurnal Teknologi, 78 (2-2). pp. 27-33. ISSN 0127-9696

[img]
Preview
PDF
518kB

Official URL: https://www.scopus.com/inward/record.uri?eid=2-s2....

Abstract

In this paper, a comparison of emotion classification undertaken by the Support Vector Machine (SVM) and the Multi-Layer Perceptron (MLP) Neural Network, using prosodic and voice quality features extracted from the Berlin Emotional Database, is reported. The features were extracted using PRAAT tools, while the WEKA tool was used for classification. Different parameters were set up for both SVM and MLP, which are used to obtain an optimized emotion classification. The results show that MLP overcomes SVM in overall emotion classification performance. Nevertheless, the training for SVM was much faster when compared to MLP. The overall accuracy was 76.82% for SVM and 78.69% for MLP. Sadness was the emotion most recognized by MLP, with accuracy of 89.0%, while anger was the emotion most recognized by SVM, with accuracy of 87.4%. The most confusing emotions using MLP classification were happiness and fear, while for SVM, the most confusing emotions were disgust and fear.

Item Type:Article
Uncontrolled Keywords:emotion recognition, voice quality features
Subjects:Q Science > QA Mathematics > QA76 Computer software
Divisions:Computing
ID Code:71237
Deposited By: Siti Nor Hashidah Zakaria
Deposited On:15 Nov 2017 04:31
Last Modified:15 Nov 2017 04:31

Repository Staff Only: item control page