By Topic

Vocal emotion recognition in five languages of Assam using features based on MFCCs and Eigen Values of Autocorrelation Matrix in presence of babble noise

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Aditya Bihar Kandali ; Department of Electrical Engineering, Indian Institute of Technology Kharagpur, Kharagpur, PIN-721302, West Bengal, India ; Aurobinda Routray ; Tapan Kumar Basu

This work investigates whether vocal emotion expressions of (i) discrete emotion be distinguished from `no-emotion' (i.e. neutral), (ii) one discrete emotion be distinguished from another, (iii) surprise, which is actually a cognitive component that could be present with any emotion, be also recognized as distinct emotion, (iv) discrete emotion be recognized cross-lingually. This study will enable us to get more information regarding nature and function of emotion. Furthermore, this work will help in developing a generalized vocal emotion recognition system, which will increase the efficiency of human-machine interaction systems. In this work, an emotional speech database consisting of short sentences of six full-blown basic emotions and neutral is created with 140 simulated utterances per speaker of five native languages of Assam. This database is validated by a Listening Test. A new feature set is proposed based on Eigen Values of Autocorrelation Matrix (EVAM) of each frame of the speech signal. The Gaussian Mixture Model (GMM) is used as classifier. The performance of the proposed feature set is compared with Mel Frequency Cepstral Coefficients (MFCCs) at sampling frequency of 8.1 kHz and with additive babble noise of 5 db and 0 db Signal-to-Noise Ratios (SNRs) under matched noise training and testing condition.

Published in:

Communications (NCC), 2010 National Conference on

Date of Conference:

29-31 Jan. 2010