首页> 外文会议>IEEE International Conference on Acoustics, Speech and Signal Processing >Meta Learning for End-To-End Low-Resource Speech Recognition
【24h】

Meta Learning for End-To-End Low-Resource Speech Recognition

机译:元学习用于端到端的低资源语音识别

获取原文

摘要

In this paper, we proposed to apply meta learning approach for low-resource automatic speech recognition (ASR). We formulated ASR for different languages as different tasks, and meta-learned the initialization parameters from many pretraining languages to achieve fast adaptation on unseen target language, via recently proposed model-agnostic meta learning algorithm (MAML). We evaluated the proposed approach using six languages as pretraining tasks and four languages as target tasks. Preliminary results showed that the proposed method, MetaASR, significantly outperforms the state-of-the-art multitask pretraining approach on all target languages with different combinations of pretraining languages. In addition, since MAML’s model-agnostic property, this paper also opens new research direction of applying meta learning to more speech-related applications.
机译:在本文中,我们提出将元学习方法应用于低资源自动语音识别(ASR)。我们通过最近提出的与模型无关的元学习算法(MAML),针对不同的语言将ASR制定为不同的任务,并从许多预训练语言中元学习了初始化参数,以实现对看不见的目标语言的快速适应。我们使用六种语言作为预训练任务和四种语言作为目标任务评估了所提出的方法。初步结果表明,在具有不同预训练语言组合的所有目标语言上,建议的方法MetaASR明显优于最新的多任务预训练方法。此外,由于MAML具有模型不可知的特性,因此本文还为将元学习应用于更多与语音相关的应用程序开辟了新的研究方向。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号