Constrained cepstral systems, which select frames to match various linguistic “constraints” in enrollment and test, have shown significant improvements for speaker verificatio...
This paper deals with the interaction between progressive model adaptation and score normalization strategies which are used for reducing the variation in likelihood ratio scores ...
We investigate various ways of generating prosodic syllable contour features that have recently been applied to enhance systems for speaker recognition. We compare different appro...
In this paper we attempt to quantify the ability of naive listeners to perform speaker recognition in the context of the NIST evaluation task. We describe our protocol: a series o...
Wade Shen, Joseph P. Campbell, Derek Straub, Reva ...
We describe a new GMM-UBM speaker recognition system that uses standard cepstral features, but selects different frames of speech for different subsystems. Subsystems, or “const...