arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2005.04290eess.AS
收藏

端到端自动语音识别的跨语言迁移学习、连续学习和领域自适应

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

Jocelyn Huang, Oleksii Kuchaiev, Patrick O'Neill, Vitaly Lavrukhin, Jason Li, Adriana Flores, Georg Kucsko, Boris Ginsburg

摘要:

在本文中,我们证明了迁移学习和连续学习的各种自动语音识别(ASR)任务的有效性。我们从一个预先训练好的英语ASR模型开始,并证明迁移学习可以在以下几个方面有效且容易地执行:(1)不同的英语口音,(2)不同的语言(德语,西班牙语和俄语)和(3)特定于应用程序的领域。我们的实验表明,在这三种情况下,从一个良好的基础模型进行迁移学习比从头开始训练的模型具有更高的准确性。与小型预训练模型相比,更倾向于微调大型模型,即使用于微调的数据集很小。此外,迁移学习显著加快了非常小和非常大的目标数据集的收敛速度。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑