TY  - JOUR
AU  - Passos, Leandro A.
AU  - Papa, João Paulo
AU  - Del Ser, Javier
AU  - Hussain, Amir
AU  - Adeel, Ahsan
PY  - 2023
DO  - 10.1016/j.inffus.2022.09.006
SN  - 1566-2535
UR  - https://hdl.handle.net/11556/5057
AB  - This paper proposes a novel multimodal self-supervised architecture for energy-efficient audio-visual (AV) speech enhancement that integrates Graph Neural Networks with canonical correlation analysis (CCA-GNN). The proposed approach lays its...
LA  - eng
TI  - Multimodal audio-visual information fusion using canonical-correlated Graph Neural Network for energy-efficient speech enhancement
TY  - journal article
ER  -