Aijun Li, Xiaolong Xu. MoMKE-AVSR: an audio–visual speech recognition framework based on mixture of modality knowledge experts. // Multimedia Systems. – 2026. – DOI: 10.1007/s00530-026-02720-0. – URL: https://doi.org/10.1007/s00530-026-02720-0
Aijun Li & Xiaolong Xu (2026). MoMKE-AVSR: an audio–visual speech recognition framework based on mixture of modality knowledge experts. Multimedia Systems. https://doi.org/10.1007/s00530-026-02720-0
Aijun Li and Xiaolong Xu. “MoMKE-AVSR: an audio–visual speech recognition framework based on mixture of modality knowledge experts.” Multimedia Systems, 2026. doi:10.1007/s00530-026-02720-0.
@article{Li2026,
title = {MoMKE-AVSR: an audio–visual speech recognition framework based on mixture of modality knowledge experts},
author = {Li, Aijun and Xu, Xiaolong},
journal = {Multimedia Systems},
year = {2026},
doi = {10.1007/s00530-026-02720-0},
url = {https://doi.org/10.1007/s00530-026-02720-0}
}