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

This video program is a part of the Premium package:

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


  • IEEE MemberUS $11.00
  • Society MemberUS $0.00
  • IEEE Student MemberUS $11.00
  • Non-IEEE MemberUS $15.00
Purchase

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

0 views
  • Share
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
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