QUT System Description to the NIST SRE 2018 Campaign

The QUT speech team has participated in the 2018 National Institute of Standard and Technology (NIST) Speaker Recognition Evaluation (SRE), and has made one primary and two contrastive submissions to the fixed condition. Our systems relies on the application of speaker embeddings termed x-vectors for developing the speaker recognition systems. In addition, we explored the use of deep auto-encoder for unsupervised domain adaptation in the embeddings subspace using unlabeled development data. We developed several subsystems which differ from features (MFCC, bottleneck (BN)), adaptation techniques, and the custom development set for adaptation. System submissions were based on a score-level fusion of up to seven subsystems. Furthermore, we produced an universal system for both domains (VAST and CMN2), calibrated the evaluation scores separately for different domain and pooled the scores for fusion.