Improving Sequence-To-Sequence Speech Recognition Training With On-The-Fly Data Augmentation

This video program is a part of the Premium package:

Improving Sequence-To-Sequence Speech Recognition Training With On-The-Fly Data Augmentation


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

Improving Sequence-To-Sequence Speech Recognition Training With On-The-Fly Data Augmentation

0 views
  • Share
Sequence-to-Sequence (S2S) models recently started to show state-of-the-art performance for automatic speech recognition (ASR). With these large and deep models overfitting remains the largest problem, outweighing performance improvements that can be obta
Sequence-to-Sequence (S2S) models recently started to show state-of-the-art performance for automatic speech recognition (ASR). With these large and deep models overfitting remains the largest problem, outweighing performance improvements that can be obta