Login / Signup

Semi-Supervised Self-Produced Speech Enhancement and Suppression Based on Joint Source Modeling of Air- and Body-Conducted Signals Using Variational Autoencoder.

Shogo SekiMoe TakadaTomoki Toda
Published in: INTERSPEECH (2020)
Keyphrases
  • semi supervised
  • speech enhancement
  • noisy environments
  • single channel
  • signal processing
  • noise reduction
  • spectral analysis
  • machine learning
  • image processing
  • multi channel
  • speech signal
  • linear prediction