# Improving Pseudo-label Training For End-to-end Speech Recognition Using Gradient Mask

arXiv: https://arxiv.org/abs/2110.04056 · HTML: https://mlsanity.com/paper/2110.04056/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 36 references that are in the map.
- First posted on arXiv 8 Oct 2021.

## Builds on (most cited first, 25 of 25)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [Learning from Noisy Labels with Deep Neural Networks: A Survey](https://mlsanity.com/paper/2007.08199/) (2020)
- [Listen, Attend and Spell](https://mlsanity.com/paper/1508.01211/) (2015)
- [Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders](https://mlsanity.com/paper/1910.12638/) (2019)
- [TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech](https://mlsanity.com/paper/2007.06028/) (2020)
- [An Unsupervised Autoregressive Model for Speech Representation Learning](https://mlsanity.com/paper/1904.03240/) (2019)
- [Improved Noisy Student Training for Automatic Speech Recognition](https://mlsanity.com/paper/2005.09629/) (2020)
- [Self-Training for End-to-End Speech Recognition](https://mlsanity.com/paper/1909.09116/) (2019)
- [Iterative Pseudo-Labeling for Speech Recognition](https://mlsanity.com/paper/2005.09267/) (2020)
- [DeCoAR 2.0: Deep Contextualized Acoustic Representations with Vector Quantization](https://mlsanity.com/paper/2012.06659/) (2020)
- [UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data](https://mlsanity.com/paper/2101.07597/) (2021)
- [Deep Contextualized Acoustic Representations For Semi-Supervised Speech Recognition](https://mlsanity.com/paper/1912.01679/) (2019)
- [RWTH ASR Systems for LibriSpeech: Hybrid vs Attention -- w/o Data Augmentation](https://mlsanity.com/paper/1905.03072/) (2019)
- [SlimIPL: Language-Model-Free Iterative Pseudo-Labeling](https://mlsanity.com/paper/2010.11524/) (2020)
- [Lessons from Building Acoustic Models with a Million Hours of Speech](https://mlsanity.com/paper/1904.01624/) (2019)
- [Joint Masked CPC and CTC Training for ASR](https://mlsanity.com/paper/2011.00093/) (2020)
- [BERTphone: Phonetically-Aware Encoder Representations for Utterance-Level Speaker and Language Recognition](https://mlsanity.com/paper/1907.00457/) (2019)
- [Exploring Pre-training with Alignments for RNN Transducer based End-to-End Speech Recognition](https://mlsanity.com/paper/2005.00572/) (2020)
- [UniSpeech at scale: An Empirical Study of Pre-training Method on Large-Scale Speech Recognition Dataset](https://mlsanity.com/paper/2107.05233/) (2021)
- [Lead2Gold: Towards exploiting the full potential of noisy transcriptions for speech recognition](https://mlsanity.com/paper/1910.07323/) (2019)

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

- [Self-Training: A Survey](https://mlsanity.com/paper/2202.12040/) (2022)
- [Decoupled Structure for Improved Adaptability of End-to-End Models](https://mlsanity.com/paper/2308.13345/) (2023)
- [Customizing Speech Recognition Model with Large Language Model Feedback](https://mlsanity.com/paper/2506.11091/) (2025)

## Abstract (arXiv)

In the recent trend of semi-supervised speech recognition, both self-supervised representation learning and pseudo-labeling have shown promising results. In this paper, we propose a novel approach to combine their ideas for end-to-end speech recognition model. Without any extra loss function, we utilize the Gradient Mask to optimize the model when training on pseudo-label. This method forces the speech recognition model to predict from the masked input to learn strong acoustic representation and make training robust to label noise. In our semi-supervised experiments, the method can improve the model performance when training on pseudo-label and our method achieved competitive results comparing with other semi-supervised approaches on the Librispeech 100 hours experiments.