Many self-supervised speech models (S3Ms) have been introduced over the ...
Spoken language understanding (SLU) tasks have been studied for many dec...
Many self-supervised speech models, varying in their pre-training object...
While transferring a pretrained language model, common approaches
conven...
Spoken language understanding (SLU) tasks involve mapping from speech au...
Progress in speech processing has been facilitated by shared datasets an...
Recently proposed self-supervised learning approaches have been successf...
It has been recognized that the joint training of computer vision tasks ...
We leverage unsupervised learning of depth, egomotion, and camera intrin...
Recent work has shown that speech paired with images can be used to lear...