Alexei Baevski
First author of wav2vec 2.0 and data2vec at Facebook AI; fairseq co-author
Alexei Baevski is first author of wav2vec 2.0, a framework for self-supervised learning of speech representations whose paper lists the authors at Facebook AI, and of data2vec, which applies one self-supervised learning method to speech, vision, and language. Baevski is also a co-author of fairseq, Facebook AI Research's MIT-licensed sequence modeling toolkit, whose repository lists wav2vec 2.0 among its examples, and of the Massively Multilingual Speech paper on scaling speech technology to more than 1,000 languages. Baevski's GitHub profile lists Google as the current company.23456781
Work
wav2vec 2.0 (external site: arxiv.org)Published research
First author of wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations (2020), with Henry Zhou, Abdelrahman Mohamed, and Michael Auli.23
data2vec (external site: arxiv.org)Published research
First author of data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language (2022); the paper says models and code are available in the fairseq repository.45
fairseq (external site: github.com)Open-source code
Co-author of fairseq: A Fast, Extensible Toolkit for Sequence Modeling (2019). The fairseq repository is published under the MIT license and lists wav2vec 2.0 (Baevski et al., 2020) among its implemented papers.67
Other documented roles
Roles the sources document but that are not confirmed as current.
- Listed with Facebook AI on the wav2vec 2.0 paper (2020), Facebook AI (Meta)3
This profile covers public professional work only, from the sources below. It is not an endorsement or a ranking. To correct or remove it, use the correction form.