Transformer-Based Acoustic Modeling For Hybrid Speech Recognition

This video program is a part of the Premium package:


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

Transformer-Based Acoustic Modeling For Hybrid Speech Recognition

0 views
  • Share
We propose and evaluate transformer-based acoustic models for hybrid speech recognition. Several modeling choices are discussed in this work, including various positional embedding methods and an iterated loss to enable training deep transformers. We also
We propose and evaluate transformer-based acoustic models for hybrid speech recognition. Several modeling choices are discussed in this work, including various positional embedding methods and an iterated loss to enable training deep transformers. We also