wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations ​

← Back to topic

Authors: Alexei Baevski, Henry Zhou, Abdel-rahman Mohamed, Michael Auli
Year: 2020
Journal: NeurIPS
DOI: 10.48550/arXiv.2006.11477
Publisher: https://arxiv.org/abs/2006.11477

Keywords: wav2vec2, ssl

Abstract ​

We present wav2vec 2.0 for self-supervised learning of speech representations.

Cite this paper ​

@misc{wav2vec22020,
  title  = {wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations},
  author = {Alexei Baevski, Henry Zhou, Abdel-rahman Mohamed, Michael Auli},
  year   = {2020},
  journal = {NeurIPS},
  doi    = {10.48550/arXiv.2006.11477},
  url    = {https://doi.org/10.48550/arXiv.2006.11477},
}

Source files ​

• metadata.json
• paper.bib