Cross-Language Transfer Learning, Continuous Learning, and Domain Adaptation for End-to-End Automatic Speech Recognition
Abstract
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.
Cite
@article{arxiv.2005.04290,
title = {Cross-Language Transfer Learning, Continuous Learning, and Domain Adaptation for End-to-End Automatic Speech Recognition},
author = {Jocelyn Huang and Oleksii Kuchaiev and Patrick O'Neill and Vitaly Lavrukhin and Jason Li and Adriana Flores and Georg Kucsko and Boris Ginsburg},
journal= {arXiv preprint arXiv:2005.04290},
year = {2020}
}