2020
ACL
ACL 2020
End-to-End Offline Speech Translation System for IWSLT 2020 using Modality Agnostic Meta-Learning
Abstract
AbstractIn 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 Speech-to-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.
🌉
Interdisciplinary Bridge
— Deep Learning and Machine Learning and Natural Language Processing and Speech & Audio
🧭
Keyword Pioneer
— synthetic data augmentation
🐝
Cross-Pollinator
— Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio
Authors
Topics
Natural Language Processing > Applications > Machine Translation
Speech & Audio > Recognition > Speech Recognition
Machine Learning > Learning Types > Meta-Learning
Natural Language Processing > Generation > Machine Translation
Deep Learning > Learning Types > Transfer Learning
Deep Learning > Learning Types > Meta-Learning