Sparse Classifier Fusion for Speaker Verification

Sparse Classifier Fusion for Speaker Verification

IEEE Transactions on Audio, Speech and Language Processing

10.1109/TASL.2013.2256895

http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6494266

Kong Aik Lee, Bin Ma, Haizhou Li, Ville Hautamäki, Tomi Kinnunen, Filip Sedlák

Computing Science

01 August 2013

V. Hautamäki, T. Kinnunen, F. Sedlák, K. A. Lee, B. Ma and H. Li, "Sparse Classifier Fusion for Speaker Verification," in IEEE Transactions on Audio, Speech, and Language Processing, vol. 21, no. 8, pp. 1622-1631, Aug. 2013, doi: 10.1109/TASL.2013.2256895.

Abstract—State-of-the-art speaker verification systems take advantage of a number of complementary base classifiers by fusing them to arrive at reliable verification decisions. In speaker verification, fusion is typically implemented as a weighted linear combination of the base classifier scores, where the combination weights are estimated using a logistic regression model. An alternative way for fusion is to use classifier ensemble selection, which can be seen as sparse regularization applied to logistic regression. Even though score fusion has been extensively studied in speaker verification, classifier ensemble selection is much less studied. In this study, we extensively study a sparse classifier fusion on a collection of twelve I4U spectral subsystems on the NIST 2008 and 2010 speaker recognition evaluation (SRE) corpora.

Publisher Copyright

There was no specific funding for the research done

The paper describes a new technique for fusion of classifiers in large-scale speaker recognition system. Classifier fusion is an essential step in state-of-the-art speaker recognition. © 2013 IEEE.  Personal use of this material is permitted.  Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

https://oar.a-star.edu.sg/communities-collections/articles/11434

1558-7916

Institute for Infocomm Research