Location-Relative Attention Mechanisms For Robust Long-Form Speech Synthesis

This video program is a part of the Premium package:

Location-Relative Attention Mechanisms For Robust Long-Form Speech Synthesis


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

Location-Relative Attention Mechanisms For Robust Long-Form Speech Synthesis

0 views
  • Share
Despite the ability to produce human-level speech for in-domain text, attention-based end-to-end text-to-speech (TTS) systems suffer from text alignment failures that increase in frequency for out-of-domain text. We show that these failures can be address
Despite the ability to produce human-level speech for in-domain text, attention-based end-to-end text-to-speech (TTS) systems suffer from text alignment failures that increase in frequency for out-of-domain text. We show that these failures can be address