On the use of X-vectors for Robust Speaker Recognition

Speaker Recognition, Embedding, X-vectors, DNN

Text-independent speaker verification (SV) is currently in the process of embracing DNN modeling in every stage of SV system. Slowly, the DNN-based approaches such as end-to-end modelling and systems based on DNN embeddings start to be competitive even in challenging and diverse channel conditions of recent NIST SREs. Domain adaptation and the need for a large amount of training data are still a challenge for current discriminative systems and (unlike with generative models), we see significant gains from data augmentation, simulation and other techniques designed to overcome lack of training data. We present an analysis of a SV system based on DNN embeddings (x-vectors) and focus on robustness across diverse data domains such as standard telephone and microphone conversations, both in clean, noisy and reverberant environments. We also evaluate the system on challenging far-field data created by re-transmitting a subset of NIST SRE 2008 and 2010 microphone interviews. We compare our results with the stateof- the-art i-vector system. In general, we were able to achieve better performance with the DNN-based systems, but most importantly, we have confirmed the robustness of such systems across multiple data domains.