Automated audio captioning challenge task is over for 2020. Here are some first details. 

Join the automated audio captioning challenge at the international DCASE 2020 challenge! 

I’m happy to announce the release of Clotho! A novel audio captioning dataset, built with focus on audio content and caption diversity, and the splits of the data are not hampering the training or evaluation of methods.

One of the very first methods for unsupervised adversarial domain adaptation for acoustic scene classification.