Login / Signup

Harmonic-Net: Fundamental Frequency and Speech Rate Controllable Fast Neural Vocoder.

Keisuke MatsubaraTakuma OkamotoRyoichi TakashimaTetsuya TakiguchiTomoki TodaHisashi Kawai
Published in: IEEE ACM Trans. Audio Speech Lang. Process. (2023)
Keyphrases
  • fundamental frequency
  • speech signal
  • network architecture
  • neural network
  • nonlinear predictive control
  • data sets
  • automatic speech recognition
  • hebbian learning