Title :
An i-vector GPLDA system for speech based emotion recognition
Author :
Kalani Wataraka Gamage;Vidhyasaharan Sethu;Phu Ngoc Le;Eliathamby Ambikairajah
Author_Institution :
School of Electrical Engineering and Telecommunications, UNSW, Australia
Abstract :
In this paper, we propose the use of a Gaussian Probabilistic Linear Discriminant Analysis (GPLDA) back-end for utterance level emotion classification based on i-vectors representing the distribution of frame level MFCC features. Experimental results based on the IEMOCAP corpus show that the GPLDA back-end outperforms an SVM based back-end while being less sensitive to i-vector dimensionality, making the proposed framework more robust to parameter tuning during system development.
Keywords :
"Feature extraction","Speech","Emotion recognition","Support vector machines","Databases","Speech recognition","Covariance matrices"
Conference_Titel :
Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2015 Asia-Pacific
DOI :
10.1109/APSIPA.2015.7415522