This study is focused on understanding and quantifying the change in pho...
Recently, Transformer-based architectures have been explored for speaker...
Several speech processing systems have demonstrated considerable perform...
In the context of keyword spotting (KWS), the replacement of handcrafted...
Adapting speaker recognition systems to new environments is a widely-use...
Automatic speaker verification systems are vulnerable to a variety of ac...
The Fearless Steps Challenge 2019 Phase-1 (FSC-P1) is the inaugural Chal...
Neural network pruning can be effectively applied to compress automatic
...
Learning an effective speaker representation is crucial for achieving
re...
Recently, attention mechanisms have been applied successfully in neural
...
Self-supervised learning representations (SSLR) have resulted in robust
...
Current leading mispronunciation detection and diagnosis (MDD) systems
a...
Audio analysis for forensic speaker verification offers unique challenge...
With the rapid development of intelligent vehicles and Advanced
Driver-A...
The goal of speech separation is to extract multiple speech sources from...
Most current speech technology systems are designed to operate well even...
In this study, we propose to investigate triplet loss for the purpose of...
Despite speaker verification has achieved significant performance improv...
With the widespread use of telemedicine services, automatic assessment o...
In forensic applications, it is very common that only small naturalistic...
Traditionally, the performance of non-native mispronunciation verificati...
Forensic audio analysis for speaker verification offers unique challenge...
In this study, we propose the global context guided channel and
time-fre...
The Fearless Steps Initiative by UTDallas-CRSS led to the digitization,
...
The reliability of using fully convolutional networks (FCNs) has been
su...
With the rapid development of intelligent vehicles and Advanced Driving
...
Speech separation refers to extracting each individual speech source in ...
Despite significant efforts over the last few years to build a robust
au...
Training acoustic models with sequentially incoming data – while both
le...
Speaker verification systems often degrade significantly when there is a...
Single-microphone, speaker-independent speech separation is normally
per...
Speaker recognition is a biometric modality that uses underlying speech
...
Attempts to develop speech enhancement algorithms with improved speech
i...
Advanced driver assistance and automated driving systems rely on risk
es...
The I4U consortium was established to facilitate a joint entry to NIST
s...
With the great achievement of artificial intelligence, vehicle technolog...
Speaker Diarization (i.e. determining who spoke and when?) for multi-spe...
In certain applications such as zero-resource speech processing or very-...
This study presents systems submitted by the University of Texas at Dall...
This document briefly describes the systems submitted by the Center for
...