Mixup-Breakdown: A Consistency Training Method For Improving Generalization Of Speech Separation Models

This video program is a part of the Premium package:

Mixup-Breakdown: A Consistency Training Method For Improving Generalization Of Speech Separation Models


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

Mixup-Breakdown: A Consistency Training Method For Improving Generalization Of Speech Separation Models

0 views
  • Share
Deep-learning based speech separation models confront poor generalization problem that even the state-of-the-art models could abruptly fail when evaluating them in mismatch conditions. To address this problem, we propose an easy-to-implement yet effective
Deep-learning based speech separation models confront poor generalization problem that even the state-of-the-art models could abruptly fail when evaluating them in mismatch conditions. To address this problem, we propose an easy-to-implement yet effective