Login / Signup

On the (In)Efficiency of Acoustic Feature Extractors for Self-Supervised Speech Representation Learning.

Titouan ParcolletShucong ZhangRogier C. van DalenAlberto Gil C. P. RamosSourav Bhattacharya
Published in: INTERSPEECH (2023)
Keyphrases
  • feature extractors
  • active learning
  • supervised learning
  • scale space
  • machine learning