← Search

Adrià Recasens

2 accepted papers

2022

Towards Learning Universal Audio Representations

ICASSP 2022accepted

The ability to learn universal audio representations that can solve diverse speech, music, and environment tasks can spur many applications that require general sound content understanding. In this work, we introduce a holistic audio representation evaluation suite (HARES) spanning 12 downstream tas…

Cited by 0SourceScholar
2021

Broaden Your Views for Self-Supervised Video Learning

ICCV 2021poster

Most successful self-supervised learning methods are trained to align the representations of two independent views from the data. State-of-the-art methods in video are inspired by image techniques, where these two views are similarly extracted by cropping and augmenting the resulting crop. However,…

Cited by 151PDFcodeScholar