Speaker recognition is a task of identifying persons from their voices. Recently, deep
learning has dramatically revolutionized speaker recognition. However, there is lack of …

This paper summarizes the applied deep learning practices in the field of speaker
recognition, both verification and identification. Speaker recognition has been a widely used …

The time delay neural network (TDNN) represents one of the state-of-the-art of neural
solutions to text-independent speaker verification. However, they require a large number of …

Time delay neural network (TDNN) has been widely used in speaker verification tasks.
Recently, two TDNN-based models, including extended TDNN (E-TDNN) and factorized …

Initially developed for natural language processing (NLP), Transformer model is now widely
used for speech processing tasks such as speaker recognition, due to its powerful sequence …

Currently, the most widely used approach for speaker verification is the deep speaker
embedding learning. In this approach, we obtain a speaker embedding vector by pooling …

The pooling mechanism plays an important role in deep neural network based systems for
text-independent speaker verification, which aggregates the variable-length frame-level …

Attention-based convolutional neural network (CNN) models are increasingly being adopted
for speaker and language recognition (SR/LR) tasks. These include time, frequency, spatial …

In this paper, we present an effective end-to-end deep embedding learning method based
on Dense-Residual networks, which combine the advantages of a densely connected …

Transformer models are now widely used for speech processing tasks due to their powerful
sequence modeling capabilities. Previous work determined an efficient way to model …