---
title: 'wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations'
license: CC-BY-4.0
license_url: https://creativecommons.org/licenses/by/4.0/
license_note: 'paper is arXiv non-exclusive distribution license (verified on arXiv abs page 2026-11-12); this pointer note is our own words and is CC BY 4.0; we link to the paper rather than reproduce it'
source: https://iinventedlight.com/library/notes/2006-11477-wav2vec-2.md
source_license: 'arXiv non-exclusive distribution license'
attribution: 'Pointer by iinventedlight (AI-assisted). Source: Alexei Baevski, Henry Zhou, Abdelrahman Mohamed, Michael Auli, wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations (arXiv non-exclusive distribution license). This note links to the paper rather than reproducing it.'
author: 'iinventedlight (AI-assisted)'
date: 2026-11-12
status: published
approved_by: "Cole Withington, 2026-11-12 14:44 PT, Librarian chat widget t51s316: \"Yes, publish all 100 second-list arXiv notes\""
checked_on: 2026-11-12
as_of: 2026-11-12
confidence: medium
untested: 'Pointer note only. Paper not reproduced. Abs page and license checked 2026-11-12.'
category: arxiv
topic_area: 'ai-research: multimodal'
tags: arxiv, multimodal, speech, self-supervised
arxiv_id: 2006.11477
alias: 2006.11477-wav2vec-2
type: pointer
format: pointer
sources:
  - id: S1
    title: 'wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations'
    publisher: arXiv
    authors: 'Alexei Baevski, Henry Zhou, Abdelrahman Mohamed, Michael Auli'
    url: https://arxiv.org/abs/2006.11477
    version_read: 'v3 (22 Oct 2020)'
    accessed: 2026-11-12
    license: 'arXiv non-exclusive distribution license'
---
# wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations

## Summary
[wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://arxiv.org/abs/2006.11477) (2020) introduced wav2vec 2.0, a self-supervised speech representation model that learns from audio alone and is then fine-tuned on transcribed speech. The authors show that this conceptually simple approach can outperform earlier semi-supervised speech methods.

What it introduced: a latent-space masking setup for speech, with a contrastive task over quantized latent representations that are learned jointly, so that a strong speech encoder can be trained before any large labeled transcript set is used.

What it led to: a standard speech backbone in the years before Whisper-style weakly supervised systems, and a template for later self-supervised audio models. Live note: [2212-04356-whisper](https://iinventedlight.com/library/notes/2212-04356-whisper/).

Use it when you are tracing speech representation learning before later all-in-one recognizers. Where to read it: https://arxiv.org/abs/2006.11477 (v3 (22 Oct 2020)).

The paper is posted on arXiv under the arXiv non-exclusive distribution license. This note links to it rather than reproducing it. The note itself is CC BY 4.0.

License: this note is CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Pointer by iinventedlight (AI-assisted). Paper license: arXiv non-exclusive distribution; this note links to it and does not reproduce it.

---

Agents: [/agents.md](/agents.md) | [/.well-known/agent-library.json](/.well-known/agent-library.json).
