@article{sadok:hal-04132316,
TITLE = {A Multimodal Dynamical Variational Autoencoder for Audiovisual Speech Representation Learning},
AUTHOR = {Sadok, Samir and Leglaive, Simon and Girin, Laurent and Alameda-Pineda, Xavier and S{\'e}guier, Renaud},
URL = {https://inria.hal.science/hal-04132316},
NOTE = {25 pages, 14 figures, https://samsad35.github.io/site-mdvae/},
JOURNAL = {Neural Networks},
PUBLISHER = {Elsevier},
VOLUME = {172},
PAGES = {106120},
YEAR = {2024},
MONTH = Apr, DOI = {10.1016/j.neunet.2024.106120},
KEYWORDS = {Audiovisual speech processing ; Deep generative modeling ; Disentangled representation learning ; Multimodal and dynamical data ; Variational autoencoder},
HAL_ID = {hal-04132316},
HAL_VERSION = {v1},
}