Login / Signup

Enhance audio generation controllability through representation similarity regularization.

Yangyang ShiGaël Le LanVarun NagarajaZhaoheng NiXinhao MeiErnie ChangForrest N. IandolaYang LiuVikas Chandra
Published in: CoRR (2023)
Keyphrases
  • similarity measure
  • multimedia
  • distance metric
  • visual information
  • euclidean distance
  • spatial location
  • cross modal