14thAnnual Conference of the International Speech Communication Association

Lyon, France
August 25-29, 2013

GMM Based Speaker Variability Compensated System for Interspeech 2013 ComParE Emotion Challenge

Vidhyasaharan Sethu (1), Julien Epps (1), Eliathamby Ambikairajah (1), Haizhou Li (2)

(1) University of New South Wales, Australia
(2) A*STAR, Singapore

This paper describes the University of New South Wales system for the Interspeech 2013 ComParE emotion sub-challenge. The primary aim of the submission is to explore the performance of model based variability compensation techniques applied to emotion classification and as a consequence of being a part of a challenge, to enable a comparison of these methods to alternative approaches. In keeping with this focused aim, a simple frame based front-end of MFCC and ĢMFCC is utilised. The systems outlined in this paper consists of a joint factor analysis based system and one based on a library of speaker-specific emotion models along with a basic GMM based system. The best combined system has an accuracy (UAR) of 47.8% as evaluated on the challenge development set and 35.7% as evaluated on the test set.

Full Paper

Bibliographic reference.  Sethu, Vidhyasaharan / Epps, Julien / Ambikairajah, Eliathamby / Li, Haizhou (2013): "GMM based speaker variability compensated system for interspeech 2013 compare emotion challenge", In INTERSPEECH-2013, 205-209.