# Censer: Curriculum Semi-supervised Learning for Speech Recognition Based on Self-supervised Pre-training

arXiv: https://arxiv.org/abs/2206.08189 · HTML: https://mlsanity.com/paper/2206.08189/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Jun 2022.

## Built on by (most cited first, 3 of 3)

- [Continuous Pseudo-Labeling from the Start](https://mlsanity.com/paper/2210.08711/) (2022)
- [Joint Speech Transcription and Translation: Pseudo-Labeling with Out-of-Distribution Data](https://mlsanity.com/paper/2212.09982/) (2022)
- [Semi-Supervised Cognitive State Classification from Speech with Multi-View Pseudo-Labeling](https://mlsanity.com/paper/2409.16937/) (2024)

## Abstract (arXiv)

Recent studies have shown that the benefits provided by self-supervised pre-training and self-training (pseudo-labeling) are complementary. Semi-supervised fine-tuning strategies under the pre-training framework, however, remain insufficiently studied. Besides, modern semi-supervised speech recognition algorithms either treat unlabeled data indiscriminately or filter out noisy samples with a confidence threshold. The dissimilarities among different unlabeled data are often ignored. In this paper, we propose Censer, a semi-supervised speech recognition algorithm based on self-supervised pre-training to maximize the utilization of unlabeled data. The pre-training stage of Censer adopts wav2vec2.0 and the fine-tuning stage employs an improved semi-supervised learning algorithm from slimIPL, which leverages unlabeled data progressively according to their pseudo labels' qualities. We also incorporate a temporal pseudo label pool and an exponential moving average to control the pseudo labels' update frequency and to avoid model divergence. Experimental results on Libri-Light and LibriSpeech datasets manifest our proposed method achieves better performance compared to existing approaches while being more unified.