Login / Signup

SoundLoCD: An Efficient Conditional Discrete Contrastive Latent Diffusion Model for Text-to-Sound Generation.

Xinlei NiuJing ZhangChristian WalderCharles Patrick Martin
Published in: ICASSP (2024)
Keyphrases
  • diffusion model
  • text generation
  • diffusion models
  • anisotropic diffusion
  • diffusion process
  • information diffusion
  • influence maximization
  • high quality
  • text mining
  • laplace transform
  • latent variables
  • wavelet transform