Web: https://syncedreview.com/2022/06/16/wav2vec-2-0-learns-brain-like-representations-from-just-600-hours-of-unlabeled-speech-data-in-new-study/

June 16, 2022, 2:30 p.m. | Synced

Synced syncedreview.com

In the new paper Toward a Realistic Model of Speech Processing in the Brain with Self-supervised Learning, researchers show that self-supervised architectures such as Wav2Vec 2.0 can learn brain-like representations from as little as 600 hours of unlabelled speech; and can also learn sound-generic and speech- and language-specific representations similar to those of the prefrontal and temporal cortices.


The post Wav2Vec 2.0 Learns Brain-Like Representations From Just 600 Hours of Unlabeled Speech Data in New Study first appeared on Synced …

ai artificial intelligence brain data deep-neural-networks machine learning machine learning & data science ml research self-supervised learning speech speech processing study technology

More from syncedreview.com / Synced

Machine Learning Researcher - Saalfeld Lab

@ Howard Hughes Medical Institute - Chevy Chase, MD | Ashburn, Virginia

Project Director, Machine Learning in US Health

@ ideas42.org | Remote, US

Data Science Intern

@ NannyML | Remote

Machine Learning Engineer NLP/Speech

@ Play.ht | Remote

Research Scientist, 3D Reconstruction

@ Yembo | Remote, US

Clinical Assistant or Associate Professor of Management Science and Systems

@ University at Buffalo | Buffalo, NY