Login / Signup
Using various pre-trained models for audio feature extraction in automated audio captioning.
Hyejin Won
Baekseung Kim
Il-Youp Kwak
Changwon Lim
Published in:
Expert Syst. Appl. (2023)
Keyphrases
</>
feature extraction
multimedia
pre trained
audio visual
image processing
probabilistic model
visual data
real time
decision trees
feature space
prior knowledge
hidden markov models
statistical model
visual information
appearance variations