Abstract: This paper addresses the problem of speaker segmentation in two speaker telephone conversations, proposing a segmentation approach based on factor analysis and a novel method for intra-session variability compensation to improve segmentation performance. The segmentation system is evaluated on the NIST Speaker Recognition Evaluation 2008 summed channel test condition, showing that intra-session variability compensation allows to obtain around a 20% relative improvement in terms of speaker segmentation error.
Index Terms: Speaker segmentation, speaker and session variability, intra-session variability.