Large-scale ASR Domain Adaptation using Self- and Semi-supervised Learning
Abstract
Self- and semi-supervised learning methods have been actively investigated to reduce labeled training data or enhance the model performance. However, the approach mostly focus on in-domain performance for public datasets. In this study, we utilize the combination of self- and semi-supervised learning methods to solve unseen domain adaptation problem in a large-scale production setting for online ASR model. This approach demonstrates that using the source domain data with a small fraction of the target domain data (3%) can recover the performance gap compared to a full data baseline: relative 13.5% WER improvement for target domain data.
- Publication:
-
arXiv e-prints
- Pub Date:
- September 2021
- DOI:
- 10.48550/arXiv.2110.00165
- arXiv:
- arXiv:2110.00165
- Bibcode:
- 2021arXiv211000165H
- Keywords:
-
- Electrical Engineering and Systems Science - Audio and Speech Processing;
- Computer Science - Computation and Language;
- Computer Science - Machine Learning;
- Computer Science - Sound
- E-Print:
- ICASSP 2022 accepted, 5 pages, 2 figures, 5 tables