M. Katz, M. Schaffner, S.E. Krüger, and A. Wendemuth (Germany)
score calibration, score fusion, speaker recognition, sup port vector machine
In this paper we investigate three approaches of calibrat ing and fusing output scores for speaker verification. To day's speaker recognition systems often consist of several subsystems that use different generative and discriminative classifiers. If subsystems like Gaussian Mixture Models (GMMs) and Support Vector Machines (SVMs) are used to obtain a final score for decision a probabilistic calibra tion of single classifier scores is important. Experiments on the NIST 2006 evaluation dataset show a performance improvement compared to the single subsystems and the standard un-calibrated fusion methods.
Important Links:
Go Back
