Login / Signup

Wasserstein GAN and Waveform Loss-Based Acoustic Model Training for Multi-Speaker Text-to-Speech Synthesis Systems Using a WaveNet Vocoder.

Yi ZhaoShinji TakakiHieu-Thi LuongJunichi YamagishiDaisuke SaitoNobuaki Minematsu
Published in: IEEE Access (2018)
Keyphrases
  • data sets
  • text to speech synthesis
  • real time
  • learning systems
  • search engine
  • intelligent systems
  • management system
  • distributed systems
  • test set
  • frequency domain