Yuwu Tang, Ying Hu, Liang He, Hao Huang. A bimodal network based on Audio-Text-Interactional-Attention with ArcFace loss for speech emotion recognition. Speech Communication, 143:21-32, 2022. [doi]
@article{TangHHH22,
title = {A bimodal network based on Audio-Text-Interactional-Attention with ArcFace loss for speech emotion recognition},
author = {Yuwu Tang and Ying Hu and Liang He and Hao Huang},
year = {2022},
doi = {10.1016/j.specom.2022.07.004},
url = {https://doi.org/10.1016/j.specom.2022.07.004},
researchr = {https://researchr.org/publication/TangHHH22},
cites = {0},
citedby = {0},
journal = {Speech Communication},
volume = {143},
pages = {21-32},
}