# Combining Unsupervised and Text Augmented Semi-Supervised Learning for Low Resourced Autoregressive Speech Recognition

arXiv: https://arxiv.org/abs/2110.15836 · HTML: https://mlsanity.com/paper/2110.15836/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 32 references that are in the map.
- First posted on arXiv 29 Oct 2021.

## Builds on (most cited first, 21 of 21)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [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)
- [ESPnet: End-to-End Speech Processing Toolkit](https://mlsanity.com/paper/1804.00015/) (2018)
- [Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learning](https://mlsanity.com/paper/1609.06773/) (2016)
- [TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech](https://mlsanity.com/paper/2007.06028/) (2020)
- [Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition](https://mlsanity.com/paper/2010.10504/) (2020)
- [An Unsupervised Autoregressive Model for Speech Representation Learning](https://mlsanity.com/paper/1904.03240/) (2019)
- [On Using Monolingual Corpora in Neural Machine Translation](https://mlsanity.com/paper/1503.03535/) (2015)
- [Improved Noisy Student Training for Automatic Speech Recognition](https://mlsanity.com/paper/2005.09629/) (2020)
- [Recent Developments on ESPnet Toolkit Boosted by Conformer](https://mlsanity.com/paper/2010.13956/) (2020)
- [Cold Fusion: Training Seq2Seq Models Together with Language Models](https://mlsanity.com/paper/1708.06426/) (2017)
- [Internal Language Model Estimation for Domain-Adaptive End-to-End Speech Recognition](https://mlsanity.com/paper/2011.01991/) (2020)
- [DeCoAR 2.0: Deep Contextualized Acoustic Representations with Vector Quantization](https://mlsanity.com/paper/2012.06659/) (2020)
- [EESEN: End-to-End Speech Recognition using Deep RNN Models and WFST-based Decoding](https://mlsanity.com/paper/1507.08240/) (2015)
- [Lessons from Building Acoustic Models with a Million Hours of Speech](https://mlsanity.com/paper/1904.01624/) (2019)
- [Comparison of Decoding Strategies for CTC Acoustic Models](https://mlsanity.com/paper/1708.04469/) (2017)
- [Overcoming Domain Mismatch in Low Resource Sequence-to-Sequence ASR Models using Hybrid Generated Pseudotranscripts](https://mlsanity.com/paper/2106.07716/) (2021)

## Built on by (most cited first, 2 of 2)

- [Training Autoregressive Speech Recognition Models with Limited in-domain Supervision](https://mlsanity.com/paper/2210.15135/) (2022)
- [TOGGL: Transcribing Overlapping Speech with Staggered Labeling](https://mlsanity.com/paper/2408.06474/) (2024)

## Abstract (arXiv)

Recent advances in unsupervised representation learning have demonstrated the impact of pretraining on large amounts of read speech. We adapt these techniques for domain adaptation in low-resource -- both in terms of data and compute -- conversational and broadcast domains. Moving beyond CTC, we pretrain state-of-the-art Conformer models in an unsupervised manner. While the unsupervised approach outperforms traditional semi-supervised training, the techniques are complementary. Combining the techniques is a 5% absolute improvement in WER, averaged over all conditions, compared to semi-supervised training alone. Additional text data is incorporated through external language models. By using CTC-based decoding, we are better able to take advantage of the additional text data. When used as a transcription model, it allows the Conformer model to better incorporate the knowledge from the language model through semi-supervised training than shallow fusion. Final performance is an additional 2% better absolute when using CTC-based decoding for semi-supervised training compared to shallow fusion.