Login / Signup

Generating Speakers by Prompting Listener Impressions for Pre-trained Multi-Speaker Text-to-Speech Systems.

Zhengyang ChenXuechen LiuErica CooperJunichi YamagishiYanmin Qian
Published in: CoRR (2024)
Keyphrases
  • text to speech
  • pre trained
  • neural network
  • prosodic features
  • data sets
  • audio visual
  • speech synthesis
  • programming tool