The NTT DCASE2020 Challenge Task 6 system: Automated Audio Captioning with Keywords and Sentence Length Estimation
Audio and Speech Processing
2020-07-02 v1 Machine Learning
Sound
Machine Learning
Abstract
This technical report describes the system participating to the Detection and Classification of Acoustic Scenes and Events (DCASE) 2020 Challenge, Task 6: automated audio captioning. Our submission focuses on solving two indeterminacy problems in automated audio captioning: word selection indeterminacy and sentence length indeterminacy. We simultaneously solve the main caption generation and sub indeterminacy problems by estimating keywords and sentence length through multi-task learning. We tested a simplified model of our submission using the development-testing dataset. Our model achieved 20.7 SPIDEr score where that of the baseline system was 5.4.
Keywords
Cite
@article{arxiv.2007.00225,
title = {The NTT DCASE2020 Challenge Task 6 system: Automated Audio Captioning with Keywords and Sentence Length Estimation},
author = {Yuma Koizumi and Daiki Takeuchi and Yasunori Ohishi and Noboru Harada and Kunio Kashino},
journal= {arXiv preprint arXiv:2007.00225},
year = {2020}
}
Comments
Technical Report of DCASE2020 Challenge Task 6