1. Home
  2. Ondemand
  3. IEEE ICASSP 2020 Virtual Conference May 2020
  4. Residual Recurrent Neural Network For Speech Enhancement

Residual Recurrent Neural Network For Speech Enhancement

Collection:
IEEE ICASSP 2020 Virtual Conference May 2020
Most current speech enhancement models use spectrogram features that require an expensive transformation and result in phase information loss. Previous work has overcome these issues by using convolutional networks to learn the temporal correlations acros
  • IEEE MemberUS $11.00
  • Society MemberUS $0.00
  • IEEE Student MemberUS $11.00
  • Non-IEEE MemberUS $15.00
Purchase

Videos in this product

Residual Recurrent Neural Network For Speech Enhancement

00:13:09
2 views
Most current speech enhancement models use spectrogram features that require an expensive transformation and result in phase information loss. Previous work has overcome these issues by using convolutional networks to learn the temporal correlations acros