Recently, deep neural networks that map utterances to fixed-dimensional embeddings have
emerged as the state-of-the-art in speaker recognition. Our prior work introduced x-vectors …

We present a thorough analysis of the systems developed by the JHU-MIT consortium in the
context of NIST speaker recognition evaluation 2018. In the previous NIST evaluation, in …

We present a condensed description of the joint effort of JHUCLSP, JHU-HLTCOE, MIT-LL.,
MIT CSAIL and LSE-EPITA for NIST SRE18. All the developed systems consisted of xvector/i …

We present a magnitude estimation network that is combined with a modified ResNet x-
vector system to generate embeddings whose inner product is able to produce calibrated …

The VoxSRC speaker recognition challenge comprises data obtained from YouTube videos
of celebrity interviews in a wide range of recording environments. The challenge provides …

State-of-the-art text-independent speaker recognition systems for long recordings (a few
minutes) are based on deep neural network (DNN) speaker embeddings. Current …

Contrary to i-vectors, speaker embeddings such as x-vectors are incapable of leveraging
unlabelled utterances, due to the classification loss over training speakers. In this paper, we …

Domain mismatch refers to the problem in which the distribution of training data differs from
that of the test data. This paper proposes a variational domain adversarial neural network …

This book will help readers understand fundamental and advanced statistical models and
deep learning models for robust speaker recognition and domain adaptation. This useful …

In this paper, we address the problem of speaker verification in conditions unseen or
unknown during development. A standard method for speaker verification consists of …