From adaptive score normalization to adaptive data normalization for speaker verification systems

Domain and trial-dependent mismatch between training and evaluation data can severely affect the performance of speaker verification systems, and are usually addressed either at embedding level, with methods that try matching the distribution of in-domain and out-of-domain data, or at score level by means of calibration and score normalization approaches. In this work we propose an alternative to score normalization that leverages the adaptive cohort selection of Adaptive S-norm (AS-norm), but performs normalization at embedding rather than at score level. Experimental results on SRE 2016 and SRE 2019 show that the proposed method is able to outperform other approaches in presence of severe mismatch, and achieves similar performance in scenarios where score normalization is less important. Furthermore, in contrast with AS-norm, our approach allows independently normalizing the enrollment and test segments, and has negligible computational cost at scoring time.Index Terms: speaker recognition, score normalization, adaptive score normalization, speaker embeddings