# Cross-Language Transfer Learning, Continuous Learning, and Domain Adaptation for End-to-End Automatic Speech Recognition

arXiv: https://arxiv.org/abs/2005.04290 · HTML: https://mlsanity.com/paper/2005.04290/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 May 2020.

## Built on by (most cited first, 9 of 9)

- [SPGISpeech: 5,000 hours of transcribed financial audio for fully formatted end-to-end speech recognition](https://mlsanity.com/paper/2104.02014/) (2021)
- [Opportunities and Challenges of Large Language Models for Low-Resource Languages in Humanities Research](https://mlsanity.com/paper/2412.04497/) (2024)
- [ASR data augmentation in low-resource settings using cross-lingual multi-speaker TTS and cross-lingual voice conversion](https://mlsanity.com/paper/2204.00618/) (2022)
- [A Simple Baseline for Domain Adaptation in End to End ASR Systems Using Synthetic Data](https://mlsanity.com/paper/2206.13240/) (2022)
- [Compressing 1D Time-Channel Separable Convolutions using Sparse Random Ternary Matrices](https://mlsanity.com/paper/2103.17142/) (2021)
- [BEA-Base: A Benchmark for ASR of Spontaneous Hungarian](https://mlsanity.com/paper/2202.00601/) (2022)
- [Coarse-To-Fine And Cross-Lingual ASR Transfer](https://mlsanity.com/paper/2109.00916/) (2021)
- [Ensemble Transfer Learning for Multilingual Coreference Resolution](https://mlsanity.com/paper/2301.09175/) (2023)
- [Closing the Speech-Text Gap with Limited Audio for Effective Domain Adaptation in LLM-Based ASR](https://mlsanity.com/paper/2604.06487/) (2026)

## Abstract (arXiv)

In this paper, we demonstrate the efficacy of transfer learning and continuous learning for various automatic speech recognition (ASR) tasks. We start with a pre-trained English ASR model and show that transfer learning can be effectively and easily performed on: (1) different English accents, (2) different languages (German, Spanish and Russian) and (3) application-specific domains. Our experiments demonstrate that in all three cases, transfer learning from a good base model has higher accuracy than a model trained from scratch. It is preferred to fine-tune large models than small pre-trained models, even if the dataset for fine-tuning is small. Moreover, transfer learning significantly speeds up convergence for both very small and very large target datasets.