INTERSPEECH 2013 14thAnnual Conference of the International Speech Communication Association Lyon, France August 25-29, 2013

Native Accent Classification via I-Vectors and Speaker Compensation Fusion

Andrea DeMarco, Stephen J. Cox

University of East Anglia, UK

We present a comprehensive analysis of the use of I-vector based classifiers for the classification of unlabelled acoustic data as native British accents. We demonstrate the different behaviours of various popular dimensionality reduction techniques that have been previously used in problems such as speaker and language classification. Our results show that a fusion of I-vector based systems gives state-of-the-art performance for unlabelled classification of British accent speech data, reaching .81% accuracy.

Full Paper

Bibliographic reference.  DeMarco, Andrea / Cox, Stephen J. (2013): "Native accent classification via i-vectors and speaker compensation fusion", In INTERSPEECH-2013, 1472-1476.