An overview and preparation for recognition of emotion from speech signal with multi modal fusion

The goal of this work is to build emotion detection system which utilizes fusion of different timescale features of speech. Conventional spectral and prosody features are used and a new information fusion algorithm which takes care of the characteristics of each machine learning algorithm will be in...

Full description

Saved in:
Bibliographic Details
Published in2010 The 2nd International Conference on Computer and Automation Engineering (ICCAE) Vol. 5; pp. 446 - 452
Main Authors Meshram, A P, Shirbahadurkar, S D, Kohok, Ashwini, Jadhav, Smita
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.02.2010
Subjects
Acoustic signal detection
Data mining
Educational institutions
Emotion recognition
Feature extraction
Fusion Algorithm
Gaussian mixture model
k-nearest neighborhood
Machine learning
Machine learning algorithms
Psychology
Speech analysis
Speech recognition
Online AccessGet full text

Cover

More Information
Summary:The goal of this work is to build emotion detection system which utilizes fusion of different timescale features of speech. Conventional spectral and prosody features are used and a new information fusion algorithm which takes care of the characteristics of each machine learning algorithm will be introduced in the paper.
ISBN:9781424455690
1424455693
1424455855
9781424455850
DOI:10.1109/ICCAE.2010.5451242