Papers › Self-training and Pre-training are Complementary for Speech Recognition

Self-training and Pre-training are Complementary for Speech Recognition

22 Oct 2020arXiv:2010.11430archive 2025-07-28

Qiantong Xu, Alexei Baevski, Tatiana Likhomanenko, Paden Tomasello, Alexis Conneau, Ronan Collobert, Gabriel Synnaeve, Michael Auli

Self-training and unsupervised pre-training have emerged as effective approaches to improve speech recognition systems using unlabeled data. However, it is not clear whether they learn similar patterns or if they can be effectively combined. In this paper, we show that pseudo-labeling and pre-training with wav2vec 2.0 are complementary in a variety of labeled data setups. Using just 10 minutes of labeled data from Libri-light as well as 53k hours of unlabeled data from LibriVox achieves WERs of 3.0%/5.2% on the clean and other test sets of Librispeech - rivaling the best published systems trained on 960 hours of labeled data only a year ago. Training on all labeled data of Librispeech achieves WERs of 1.5%/3.1%.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

pytorch/fairseq officialmentioned in papermentioned on GitHubpytorch report
pytorch/fairseq officialpytorch report
facebookresearch/fairseq mentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Speech RecognitionUnsupervised Pre-trainingspeech-recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Speech Recognition LibriSpeech test-clean Conv + Transformer + wav2vec2.0 + pseudo labeling Word Error Rate (WER) 1.5 #7 of 64 Archive leaderboard report
Speech Recognition LibriSpeech test-clean wav2vec_wav2letter Word Error Rate (WER) 2.7 #43 of 64 Archive leaderboard report
Speech Recognition LibriSpeech test-other Conv + Transformer + wav2vec2.0 + pseudo labeling Word Error Rate (WER) 3.1 #7 of 53 Archive leaderboard report
Speech Recognition LibriSpeech train-clean-100 test-clean wav2vec_wav2letter Word Error Rate (WER) 2.8 #1 of 1 Archive leaderboard report
Speech Recognition LibriSpeech train-clean-100 test-other wav2vec_wav2letter Word Error Rate (WER) 3.6 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections