Login / Signup

How Should We Extract Discrete Audio Tokens from Self-Supervised Models?

Pooneh MousaviJarod DuretSalah ZaiemLuca Della LiberaArtem PloujnikovCem SubakanMirco Ravanelli
Published in: CoRR (2024)
Keyphrases
  • multimedia
  • parametric models
  • neural network
  • machine learning
  • information retrieval
  • feature vectors
  • low level
  • statistical models