| Paper | Code | Word Error Rate (WER) | ABX-across | ABX-within | ModelName | ReleaseDate |
|---|---|---|---|---|---|---|
| wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations | ✓ Link | 2.5 | wav2vec 2.0 Large-10h-LV-60k | 2020-06-20 | ||
| Libri-Light: A Benchmark for ASR with Limited or No Supervision | ✓ Link | 29.3 | TDS 60k pseudo-label + CTC fine-tuning + 4gram-LM | 2019-12-17 | ||
| Libri-Light: A Benchmark for ASR with Limited or No Supervision | ✓ Link | 43.9 | CPC unlab-60k+train-10h CPC pretrain + CTC fine-tuning + 4gram-LM | 2019-12-17 | ||
| Libri-Light: A Benchmark for ASR with Limited or No Supervision | ✓ Link | 7.56 | 5.83 | CPC unlab-60k | 2019-12-17 | |
| Improving Unsupervised Sparsespeech Acoustic Models with Categorical Reparameterization | ✓ Link | 13.53 | 9.33 | S6000h-n42-τ2 → 0.1 | 2020-05-29 |