Speaker-Aware Training Of Attention-Based End-To-End Speech Recognition Using Neural Speaker Embeddings

This video program is a part of the Premium package:

Speaker-Aware Training Of Attention-Based End-To-End Speech Recognition Using Neural Speaker Embeddings


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

Speaker-Aware Training Of Attention-Based End-To-End Speech Recognition Using Neural Speaker Embeddings

0 views
  • Share
Create Account or Sign In to post comments
In speaker-aware training, a speaker embedding is appended to DNN input features. This allows the DNN to effectively learn representations, which are robust to speaker variability. We apply speaker-aware training to attention-based end-to-end speech recog
In speaker-aware training, a speaker embedding is appended to DNN input features. This allows the DNN to effectively learn representations, which are robust to speaker variability. We apply speaker-aware training to attention-based end-to-end speech recog