Joint Phoneme-Grapheme Model For End-To-End Speech Recognition

This video program is a part of the Premium package:

Joint Phoneme-Grapheme Model For End-To-End Speech Recognition


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

Joint Phoneme-Grapheme Model For End-To-End Speech Recognition

0 views
  • Share
Create Account or Sign In to post comments
This paper proposes methods to improve a commonly used end-to-end speech recognition model, Listen-Attend-Spell (LAS). The methods we proposed use multi-task learning to improve generalization of the model by leveraging information from multiple labels. T
This paper proposes methods to improve a commonly used end-to-end speech recognition model, Listen-Attend-Spell (LAS). The methods we proposed use multi-task learning to improve generalization of the model by leveraging information from multiple labels. T