Huang Xie, Okko Räsänen, Konstantinos Drossos, Tuomas Virtanen. Unsupervised Audio-Caption Aligning Learns Correspondences Between Individual Sound Events and Textual Phrases. In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022, Virtual and Singapore, 23-27 May 2022. pages 8867-8871, IEEE, 2022. [doi]
@inproceedings{XieRDV22, title = {Unsupervised Audio-Caption Aligning Learns Correspondences Between Individual Sound Events and Textual Phrases}, author = {Huang Xie and Okko Räsänen and Konstantinos Drossos and Tuomas Virtanen}, year = {2022}, doi = {10.1109/ICASSP43922.2022.9747336}, url = {https://doi.org/10.1109/ICASSP43922.2022.9747336}, researchr = {https://researchr.org/publication/XieRDV22}, cites = {0}, citedby = {0}, pages = {8867-8871}, booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022, Virtual and Singapore, 23-27 May 2022}, publisher = {IEEE}, isbn = {978-1-6654-0540-9}, }