Samuel Lipping, Konstantinos Drossos, Tuomas Virtanen. Crowdsourcing a Dataset of Audio Captions. In Michael I. Mandel, Justin Salamon, Daniel P. W. Ellis, editors, Proceedings of the Workshop on Detection and Classification of Acoustic Scenes and Events 2019 (DCASE 2019), New York University, NY, USA, October 2019. pages 139-143, 2019. [doi]
@inproceedings{LippingDV19,
title = {Crowdsourcing a Dataset of Audio Captions},
author = {Samuel Lipping and Konstantinos Drossos and Tuomas Virtanen},
year = {2019},
url = {http://dcase.community/documents/workshop2019/proceedings/DCASE2019Workshop_Lipping_31.pdf},
researchr = {https://researchr.org/publication/LippingDV19},
cites = {0},
citedby = {0},
pages = {139-143},
booktitle = {Proceedings of the Workshop on Detection and Classification of Acoustic Scenes and Events 2019 (DCASE 2019), New York University, NY, USA, October 2019},
editor = {Michael I. Mandel and Justin Salamon and Daniel P. W. Ellis},
isbn = {978-0-578-59596-2},
}