Conformer, a convolution-augmented Transformer variant, has become the d...
Self-supervised speech representation learning (SSL) has shown to be
eff...
Self-supervised pre-trained transformers have improved the state of the ...
Conformer, combining convolution and self-attention sequentially to capt...
Automatic speech recognition (ASR) models make fewer errors when more
su...
In many scenarios of a language identification task, the user will speci...
In this paper, we present a novel system that separates the voice of a t...