Sign in
BLAT: Bootstrapping Language-Audio Pre-training based on AudioSet Tag-guided Synthetic Data.
Xuenan Xu
Zhiling Zhang
Zelin Zhou
Pingyue Zhang
Zeyu Xie
Mengyue Wu
Kenny Q. Zhu
Published in:
CoRR (2023)
Keyphrases
</>
synthetic data
real image data
data sets
multimedia
human language
real world
language learning
natural language
programming language
training set
mri data
training examples
training process
audio visual
training phase
text to speech
database