Improving Proper Noun Recognition In End-To-End Asr By Customization Of The Mwer Loss Criterion

This video program is a part of the Premium package:

Improving Proper Noun Recognition In End-To-End Asr By Customization Of The Mwer Loss Criterion


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

Improving Proper Noun Recognition In End-To-End Asr By Customization Of The Mwer Loss Criterion

0 views
  • Share
Proper nouns present a challenge for end-to-end (E2E) automatic speech recognition (ASR) systems in that a particular name may appear only rarely during training, and may have a pronunciation similar to that of a more common word. Unlike conventional ASR
Proper nouns present a challenge for end-to-end (E2E) automatic speech recognition (ASR) systems in that a particular name may appear only rarely during training, and may have a pronunciation similar to that of a more common word. Unlike conventional ASR