Full-covariance UBM and heavy-tailed PLDA in i-vector speaker verification

In this paper, we describe recent progress in i-vector based speaker verification. The use of universal background models (UBM) with full-covariance matrices is suggested and thoroughly experimentally tested. The i-vectors are scored using a simple cosine distance and advanced techniques such as Probabilistic Linear Discriminant Analysis (PLDA) and heavy-tailed variant of PLDA (PLDA-HT). Finally, we investigate into dimensionality reduction of i-vectors before entering the PLDA-HT modeling. The results are very competitive: on NIST 2010 SRE task, the results of a single full-covariance LDA-PLDA-HT system approach those of complex fused system.

• Type: Journal
• Year: 2011
• Where: ICASSP
• Authors: Pavel Matejka, Ondrej Glembek, Fabio Castaldo, M. J. Alam, Oldrich Plchot, Patrick Kenny, Lukas Burget, Jan Cernocký
• Keywords: ICASSP 2011, Nist 2010 Sre, Signal Processing, Simple Cosine Distance, Universal Background Models