The NTT DCASE2020 Challenge Task 6 system: Automated Audio Captioning with Keywords and Sentence Length Estimation

07/01/2020

∙

by   Yuma Koizumi, et al.

∙

0

∙

share

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.