论文标题
跨语言转移学习，持续学习和域名自动语音识别的适应性
Cross-Language Transfer Learning, Continuous Learning, and Domain Adaptation for End-to-End Automatic Speech Recognition
论文作者
论文摘要
在本文中，我们证明了转移学习和持续学习的功效，以实现各种自动语音识别（ASR）任务。我们从预先训练的英语ASR模型开始，并表明转移学习可以有效，很容易地进行：（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）（3）特定于应用的域。我们的实验表明，在所有三种情况下，从良好的基本模型中转移学习的精度都比从头开始训练的模型更高。即使用于微调的数据集很小，它也比小型预训练的模型更喜欢微型模型。此外，转移学习可以显着加快目标数据集和非常大的目标数据集的融合。
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.
