@INPROCEEDINGS{drossos:eusipco:2021, 
author={A. Tran and K. Drossos and T. Virtanen}, 
booktitle={29th European Signal Processing Conference ({EUSIPCO})}, 
title={WaveTransformer: An Architecture for Audio Captioning Based on Learning Temporal and Time-Frequency Information}, 
year={2021},
pages={}, 
doi={}, 
ISSN={}, 
month={Aug.},}