Transfer learning has proven to be crucial in advancing the state of spe...
Self-supervised Speech Models (S3Ms) have been proven successful in many...
Previous works have shown that automatic speaker verification (ASV) is
s...
Self-supervised learning (SSL) has proven vital for advancing research i...
Automatic speaker verification (ASV) is one of the core technologies in
...
We introduce a self-supervised speech pre-training method called TERA, w...
Self-supervised Audio Transformers (SAT) enable great success in many
do...
High-performance anti-spoofing models for automatic speaker verification...
Recently, neural vocoders have been widely used in speech synthesis task...
We present Mockingjay as a new speech representation learning approach, ...
We present an unsupervised end-to-end training scheme where we discover
...