Masked Spectrogram Prediction For Self-Supervised Audio Pre-Training.

Dading Chong Helin Wang Peilin Zhou Qingcheng Zeng

Published in: CoRR (2022)

Keyphrases

prediction accuracy
multimedia
prediction algorithm
multi layer perceptron
visual information
prediction model
pattern analysis
training algorithm
training phase
audio video
artificial neural networks
training examples
audio stream
predictive model
training samples
supervised learning
training set
feature space