Login / Signup

DiveSound: LLM-Assisted Automatic Taxonomy Construction for Diverse Audio Generation.

Baihan LiZeyu XieXuenan XuYiwei GuoMing YanJi ZhangKai YuMengyue Wu
Published in: CoRR (2024)
Keyphrases
  • wide variety
  • multimedia
  • multi modal
  • fully automatic
  • audio visual
  • generation process
  • generation method
  • audio signals
  • databases
  • feature vectors
  • data driven
  • semi automatic
  • cross modal
  • speech music discrimination