Speaker recognition in two-wire test sessions

Abstract

This paper deals with the task of speaker recognition in four-wire training and two-wire testing conditions. Instead of performing blind speaker diarization before the recognition stage, we directly perform the recognition on the non-segmented (or imperfectly diarized) speech. We present an analysis of the problem with respect to three different speaker recognition systems and propose improved recognition techniques both in the frame domain and in the model domain. The proposed techniques reduce error rate significantly. Furthermore, the developed techniques may be also beneficial in conjunction with an imperfect blind diarization stage. Copyright © 2008 ISCA.