Login / Signup

Unsupervised Face-Masked Speech Enhancement Using Generative Adversarial Networks With Human-in-the-Loop Assessment Metrics.

Syu-Siang WangJia-Yang ChenBo-Ren BaiShih-Hau FangYu Tsao
Published in: IEEE ACM Trans. Audio Speech Lang. Process. (2024)
Keyphrases
  • speech enhancement
  • generative model
  • noise reduction
  • pattern recognition
  • noisy environments
  • signal to noise ratio
  • bayesian networks
  • maximum likelihood
  • speech signal
  • vocal tract