# Improving noisy student training for low-resource languages in End-to-End ASR using CycleGAN and inter-domain losses

arXiv: https://arxiv.org/abs/2407.21061 · HTML: https://mlsanity.com/paper/2407.21061/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 39 references that are in the map.
- First posted on arXiv 26 Jul 2024.

## Builds on (most cited first, 23 of 23)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [ESPnet: End-to-End Speech Processing Toolkit](https://mlsanity.com/paper/1804.00015/) (2018)
- [Libri-Light: A Benchmark for ASR with Limited or No Supervision](https://mlsanity.com/paper/1912.07875/) (2019)
- [vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations](https://mlsanity.com/paper/1910.05453/) (2019)
- [Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learning](https://mlsanity.com/paper/1609.06773/) (2016)
- [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)
- [End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architectures](https://mlsanity.com/paper/1911.08460/) (2019)
- [Unsupervised speech representation learning using WaveNet autoencoders](https://mlsanity.com/paper/1901.08810/) (2019)
- [Deep Contextualized Acoustic Representations For Semi-Supervised Speech Recognition](https://mlsanity.com/paper/1912.01679/) (2019)
- [SpecAugment on Large Scale Datasets](https://mlsanity.com/paper/1912.05533/) (2019)
- [Speech2Vec: A Sequence-to-Sequence Framework for Learning Word Embeddings from Speech](https://mlsanity.com/paper/1803.08976/) (2018)
- [Listening while Speaking: Speech Chain by Deep Learning](https://mlsanity.com/paper/1707.04879/) (2017)
- [Cycle-consistency training for end-to-end speech recognition](https://mlsanity.com/paper/1811.01690/) (2018)
- [Back-Translation-Style Data Augmentation for End-to-End ASR](https://mlsanity.com/paper/1807.10893/) (2018)
- [Lessons from Building Acoustic Models with a Million Hours of Speech](https://mlsanity.com/paper/1904.01624/) (2019)
- [Multi-Modal Data Augmentation for End-to-End ASR](https://mlsanity.com/paper/1803.10299/) (2018)
- [Extracting Domain Invariant Features by Unsupervised Learning for Robust Automatic Speech Recognition](https://mlsanity.com/paper/1803.02551/) (2018)
- [Improving Semi-supervised End-to-end Automatic Speech Recognition using CycleGAN and Inter-domain Losses](https://mlsanity.com/paper/2210.11642/) (2022)

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

- [Fotheidil: an Automatic Transcription System for the Irish Language](https://mlsanity.com/paper/2501.00509/) (2024)
- [LESS: Large Language Model Enhanced Semi-Supervised Learning for Speech Foundational Models Using in-the-wild Data](https://mlsanity.com/paper/2506.04586/) (2025)

## Abstract (arXiv)

Training a semi-supervised end-to-end speech recognition system using noisy student training has significantly improved performance. However, this approach requires a substantial amount of paired speech-text and unlabeled speech, which is costly for low-resource languages. Therefore, this paper considers a more extreme case of semi-supervised end-to-end automatic speech recognition where there are limited paired speech-text, unlabeled speech (less than five hours), and abundant external text. Firstly, we observe improved performance by training the model using our previous work on semi-supervised learning "CycleGAN and inter-domain losses" solely with external text. Secondly, we enhance "CycleGAN and inter-domain losses" by incorporating automatic hyperparameter tuning, calling it "enhanced CycleGAN inter-domain losses." Thirdly, we integrate it into the noisy student training approach pipeline for low-resource scenarios. Our experimental results, conducted on six non-English languages from Voxforge and Common Voice, show a 20% word error rate reduction compared to the baseline teacher model and a 10% word error rate reduction compared to the baseline best student model, highlighting the significant improvements achieved through our proposed method.