Discriminative training and channel compensation for acoustic language recognition
Valiantsina Hubeika, Lukáš Burget, Pavel Matějka, Petr Schwarz · 2008
This paper describes the acoustic language recognition subsystems of Brno University of Technology (BUT) which contributed to the BUT main submission to the NIST LRE 2007. Two main techniques are employed in the subsystems discriminative training in terms of Maximum Mutual Information, and channel compensation in terms of eigenchannel adaptation in both, model and feature domain. The complementarity of the approaches is analyzed.