Login / Signup

Two-stage training method for Japanese electrolaryngeal speech enhancement based on sequence-to-sequence voice conversion.

Ding MaLester Phillip VioletaKazuhiro KobayashiTomoki Toda
Published in: CoRR (2022)
Keyphrases
  • similarity measure
  • pairwise
  • neural network
  • feature extraction
  • hybrid method
  • linear prediction