@inproceedings{8b523edd74fd4613a289ffd7b4c7dc9d,
title = "S2I-BIRD: Sound-to-image generation of bird species using generative adversarial networks",
abstract = "Generating images from sound is a challenging task. This paper proposes a novel deep learning model that generates bird images from their corresponding sound information. Our proposed model includes a sound encoder in order to extract suitable feature representations from audio recordings, and then it generates bird images that corresponds to its calls using conditional generative adversarial networks (cGANs) with auxiliary classifiers. We demonstrate that our model produces better image generation results which outperforms other state-of-the-art methods in a similar context.",
author = "Shim, {Joo Yong} and Joongheon Kim and Kim, {Jong Kook}",
note = "Funding Information: This research was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (NRF-2016R1D1A1B04933156) Publisher Copyright: {\textcopyright} 2020 IEEE; 25th International Conference on Pattern Recognition, ICPR 2020 ; Conference date: 10-01-2021 Through 15-01-2021",
year = "2020",
doi = "10.1109/ICPR48806.2021.9412721",
language = "English",
series = "Proceedings - International Conference on Pattern Recognition",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "2226--2232",
booktitle = "Proceedings of ICPR 2020 - 25th International Conference on Pattern Recognition",
}