Login / Signup

Jointly Fine-Tuning "BERT-Like" Self Supervised Models to Improve Multimodal Speech Emotion Recognition.

Shamane SiriwardhanaAndrew ReisRivindu WeerasekeraSuranga Nanayakkara
Published in: INTERSPEECH (2020)
Keyphrases
  • fine tuning
  • speech emotion recognition
  • viable alternative
  • fine tune
  • pairwise
  • fine tuned
  • data sets
  • information systems
  • mutual information
  • model selection
  • parameter estimation
  • statistical model
  • statistical models