Corpora for Speaker Recognition Research and Evaluation in Oriya

Abstract

Automatic speaker recognition (ASR) refers to the detection of a person's identity from his/her voice with the help of machines. ASR finds its potential applications in telephone based financial transactions, purchase of credit card, information retrieval for surveillance in defense and intelligence organization and study of different dialects in a particular language. In this paper, we describe the methodology and a typical experimental setup used for building up speech corpora for the text-independent speaker recognition in Indian language, viz., Oriya. Finally, an ASR system is presented for speaker identification and classification experiments.