Cross-Language Transfer Learning and Domain Adaptation for End-to-End Automatic Speech Recognition
Lists
Only you see this
Abstract
In this paper, we demonstrate the efficacy of transfer learning and continuous learning for various automatic speech recognition (ASR) tasks using end-to-end models trained with CTC loss. We start with a large pre-trained English ASR model and show that transfer learning can be effectively and easily performed on: (1) different English accents, (2) different languages (from English to German, Spanish, Russian, or from Mandarin to Cantonese) and (3) application-specific domains. Our extensive set of experiments demonstrate that in all three cases, transfer learning from a good base model has higher accuracy than a model trained from scratch. Our results indicate that, for fine-tuning, larger pre-trained models are better than small pre-trained models, even if the dataset for fine-tuning is small. We also show that transfer learning significantly speeds up convergence, which could result in significant cost savings when training with large datasets.
BibTeX
@inproceedings{luo2021cross,
author = {Jian Luo and Jianzong Wang and Ning Cheng and Edward Xiao and Jing Xiao and Georg Kucsko and Patrick K. O'Neill and Jagadeesh Balam and Slyne Deng and Adriana Flores and Boris Ginsburg and Jocelyn Huang and Oleksii Kuchaiev and Vitaly Lavrukhin and Jason Li},
title = {{Cross-Language Transfer Learning and Domain Adaptation for End-to-End Automatic Speech Recognition}},
booktitle = {ICME},
year = {2021},
doi = {10.1109/icme51207.2021.9428334},
}Loading related content...