Login / Signup

Supervised model training for overlapping sound events based on unsupervised source separation.

Toni HeittolaAnnamaria MesarosTuomas VirtanenMoncef Gabbouj
Published in: ICASSP (2013)
Keyphrases
  • training set
  • supervised learning
  • high level
  • multiresolution
  • dimensionality reduction
  • unsupervised learning