Xuenan Xu, Heinrich Dinkel, Mengyue Wu, Kai Yu 0004. Text-to-Audio Grounding: Building Correspondence Between Captions and Sound Events. In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2021, Toronto, ON, Canada, June 6-11, 2021. pages 606-610, IEEE, 2021. [doi]
@inproceedings{XuDW021-0,
title = {Text-to-Audio Grounding: Building Correspondence Between Captions and Sound Events},
author = {Xuenan Xu and Heinrich Dinkel and Mengyue Wu and Kai Yu 0004},
year = {2021},
doi = {10.1109/ICASSP39728.2021.9414834},
url = {https://doi.org/10.1109/ICASSP39728.2021.9414834},
researchr = {https://researchr.org/publication/XuDW021-0},
cites = {0},
citedby = {0},
pages = {606-610},
booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2021, Toronto, ON, Canada, June 6-11, 2021},
publisher = {IEEE},
isbn = {978-1-7281-7605-5},
}