Cross-modal distillation with audio-text fusion for fine-grained emotion classification using BERT and Wav2vec 2.0.

Donghwa Kim Pilsung Kang

Published in: Neurocomputing (2022)

Keyphrases

fine grained
cross modal
multi modal
lexical features
image retrieval
syntactic analysis
access control
visual data
text retrieval
sentence level
multimedia databases
keywords
information retrieval
audio visual
emotion recognition
text mining
text documents
video search
topic models