Cheng Luo, Yiguang Liu, Wenhui Sun, Zhoujian Sun. Multi-Modality Speech Recognition Driven by Background Visual Scenes. In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2024, Seoul, Republic of Korea, April 14-19, 2024. pages 10926-10930, IEEE, 2024. [doi]
@inproceedings{LuoLSS24,
title = {Multi-Modality Speech Recognition Driven by Background Visual Scenes},
author = {Cheng Luo and Yiguang Liu and Wenhui Sun and Zhoujian Sun},
year = {2024},
doi = {10.1109/ICASSP48485.2024.10446142},
url = {https://doi.org/10.1109/ICASSP48485.2024.10446142},
researchr = {https://researchr.org/publication/LuoLSS24},
cites = {0},
citedby = {0},
pages = {10926-10930},
booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2024, Seoul, Republic of Korea, April 14-19, 2024},
publisher = {IEEE},
isbn = {979-8-3503-4485-1},
}