Login / Signup
CoNeTTE: An Efficient Audio Captioning System Leveraging Multiple Datasets With Task Embedding.
Etienne Labbé
Thomas Pellegrini
Julien Pinquier
Published in:
IEEE ACM Trans. Audio Speech Lang. Process. (2024)
Keyphrases
</>
multimedia
data sets
neural network
learning algorithm
information retrieval
search engine
decision trees
training data
multi modal
computationally efficient
broadcast news