# Coarse-To-Fine And Cross-Lingual ASR Transfer

arXiv: https://arxiv.org/abs/2109.00916 · HTML: https://mlsanity.com/paper/2109.00916/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 27 references that are in the map.
- First posted on arXiv 2 Sep 2021.

## Builds on (most cited first, 17 of 17)

- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [A Survey on Deep Transfer Learning](https://mlsanity.com/paper/1808.01974/) (2018)
- [NeMo: a toolkit for building AI applications using Neural Modules](https://mlsanity.com/paper/1909.09577/) (2019)
- [A Comparative Study on Transformer vs RNN in Speech Applications](https://mlsanity.com/paper/1909.06317/) (2019)
- [State-of-the-art Speech Recognition With Sequence-to-Sequence Models](https://mlsanity.com/paper/1712.01769/) (2017)
- [Transfer Learning for Low-Resource Neural Machine Translation](https://mlsanity.com/paper/1604.02201/) (2016)
- [Coarse-to-Fine Decoding for Neural Semantic Parsing](https://mlsanity.com/paper/1805.04793/) (2018)
- [QuartzNet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutions](https://mlsanity.com/paper/1910.10261/) (2019)
- [Jasper: An End-to-End Convolutional Neural Acoustic Model](https://mlsanity.com/paper/1904.03288/) (2019)
- [Trivial Transfer Learning for Low-Resource Neural Machine Translation](https://mlsanity.com/paper/1809.00357/) (2018)
- [Transfer Learning for Speech and Language Processing](https://mlsanity.com/paper/1511.06066/) (2015)
- [Multilingual sequence-to-sequence speech recognition: architecture, transfer learning, and language modeling](https://mlsanity.com/paper/1810.03459/) (2018)
- [Transfer Learning for Speech Recognition on a Budget](https://mlsanity.com/paper/1706.00290/) (2017)
- [Towards Language-Universal End-to-End Speech Recognition](https://mlsanity.com/paper/1711.02207/) (2017)
- [State-of-the-Art Speech Recognition Using Multi-Stream Self-Attention With Dilated 1D Convolutions](https://mlsanity.com/paper/1910.00716/) (2019)
- [Cross-Language Transfer Learning, Continuous Learning, and Domain Adaptation for End-to-End Automatic Speech Recognition](https://mlsanity.com/paper/2005.04290/) (2020)

## Abstract (arXiv)

End-to-end neural automatic speech recognition systems achieved recently state-of-the-art results, but they require large datasets and extensive computing resources. Transfer learning has been proposed to overcome these difficulties even across languages, e.g., German ASR trained from an English model. We experiment with much less related languages, reusing an English model for Czech ASR. To simplify the transfer, we propose to use an intermediate alphabet, Czech without accents, and document that it is a highly effective strategy. The technique is also useful on Czech data alone, in the style of coarse-to-fine training. We achieve substantial eductions in training time as well as word error rate (WER).