Login / Signup

A Unified Framework for the Generation of Glottal Signals in Deep Learning-based Parametric Speech Synthesis Systems.

Min-Jae HwangEunwoo SongJin-Seob KimHong-Goo Kang
Published in: INTERSPEECH (2018)
Keyphrases
  • deep learning
  • speech synthesis
  • machine learning
  • computer vision
  • text to speech
  • data sets
  • learning algorithm
  • feature selection
  • face recognition
  • multiscale
  • object detection
  • speech recognition
  • deep architectures