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

Baevski et al., 2020, wav2vec 2.0 (Advances in Neural Information Processing Systems 33 (NeurIPS 2020))

Subscriber deck — free during early access

1 cards in “6 Conclusion” · whole deck

6 Conclusion

What broader impact did the wav2vec 2.0 authors expect?
Speech recognition with very small amounts of transcribed data could make the technology available for many more of the world’s languages and dialects, most of which lack the hundreds or thousands of labelled hours current systems need.
- Baevski et al., 2020, wav2vec 2.0 (Advances in Neural Information Processing Systems 33 (NeurIPS 2020)), §6

Source

Alexei Baevski, Henry Zhou, Abdelrahman Mohamed and Michael Auli. 2020. wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations. In Advances in Neural Information Processing Systems 33 (NeurIPS 2020). https://papers.nips.cc/paper/2020/hash/92d1e1eb1cd6f9fba3227870bb6d7f07-Abstract.html