End-to-End Offline Speech Translation System for IWSLT 2020 using Modality Agnostic Meta-Learning
Nikhil Kumar Lakumarapu, Beomseok Lee, Sathish Reddy Indurthi, HouJeung Han, Mohd Abbas Zaidi, Sang‐Ha Kim · 2020
In this paper, we describe the system submitted to the IWSLT 2020 Offline Speech Translation Task.We adopt the Transformer architecture coupled with the meta-learning approach to build our end-to-end Speechto-Text Translation (ST) system.Our meta-learning approach tackles the data scarcity of the ST task by leveraging the data available from Automatic Speech Recognition (ASR) and Machine Translation (MT) tasks.The meta-learning approach combined with synthetic data augmentation techniques improves the model performance significantly and achieves BLEU scores of 24.58, 27.51, and 27.61 on IWSLT test 2015, MuST-C test, and Europarl-ST test sets respectively.