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 “5.2 High-Resource Labeled Data Evaluation on Librispeech” · whole deck
5.2 High-Resource Labeled Data Evaluation on Librispeech
- How did wav2vec 2.0 do with all 960 h of labelled LibriSpeech?1.8/3.3 WER on test-clean/other, state of the art on noisy speech, despite a weaker setup than competitors: CTC rather than seq2seq, character rather than word-piece units, and no data balancing. The same architecture trained from scratch got 2.1/4.6.
- Baevski et al., 2020, wav2vec 2.0 (Advances in Neural Information Processing Systems 33 (NeurIPS 2020)), §5.2
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