Login / Signup

VQ-CL: Learning Disentangled Speech Representations with Contrastive Learning and Vector Quantization.

Huaizhen TangXulong ZhangJianzong WangNing ChengJing Xiao
Published in: ICASSP (2023)
Keyphrases
  • vector quantization
  • image compression
  • supervised learning
  • neural network
  • multiscale
  • structural information