Title: Using MMSE to improve session variability estimation

Authors: Gang Wang, Thomas Fang Zheng

Addresses: Center for Speech and Language Technologies, Division of Technical Innovation and Development, Tsinghua National Laboratory for Information Science and Technology, Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China. ' Center for Speech and Language Technologies, Division of Technical Innovation and Development, Tsinghua National Laboratory for Information Science and Technology, Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China

Abstract: In this paper, the Session Variability Subspace Projection (SVSP) method based on model compensation for speaker verification was improved using the Minimum Mean Square Error (MMSE) criterion. The issue of SVSP is that the speaker|s session-independent supervector is approximated by the average of all his or her session-dependent GMM-supervectors when estimating SVSP matrix. However, the error between them does obviously exist. Our goal is to minimise it using MMSE criterion. Compared with the original SVSP, the proposed method could achieve an error rate reduction of 6.7% for EER and 5.3% for minimum detection cost function over the NIST SRE 2006 1C4W-dataset.

Keywords: speaker verification; session variability; MMSE; model compensation; minimum mean square error; biometrics.

DOI: 10.1504/IJBM.2010.035449

International Journal of Biometrics, 2010 Vol.2 No.4, pp.350 - 357

Published online: 30 Sep 2010 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article