A vector quantized masked autoencoder for speech emotion recognition.

Samir Sadok Simon Leglaive Renaud Séguier

Published in: CoRR (2023)

Keyphrases

speech emotion recognition
vector quantized
vector quantization
image compression
progressive transmission

visual words
bag of words
block coding
vector quantizer
bitstream

color palette
codebook design
reduced complexity
fractal image compression
machine learning

image coding
text mining
image features
face recognition
image processing