Login / Signup
Towards Robust Family-Infant Audio Analysis Based on Unsupervised Pretraining of Wav2vec 2.0 on Large-Scale Unlabeled Family Audio.
Jialu Li
Mark Hasegawa-Johnson
Nancy L. McElwain
Published in:
INTERSPEECH (2023)
Keyphrases
</>
multimedia
unsupervised learning
data analysis
audio video
image analysis
special case
small scale
neural network
training data
real life
prior knowledge
signal processing
data driven
audio visual
audio signals
music score