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

Relative validation accuracy during training

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.

Type
Publication
In 2021 IEEE International Conference on Multimedia and Expo
Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.
Jian Luo
Jian Luo
Researcher
Ning Cheng
Ning Cheng
Director