2018
EMNLP
EMNLP 2018
The JHU/KyotoU Speech Translation System for IWSLT 2018
Abstract
AbstractThis paper describes the Johns Hopkins University (JHU) and Kyoto University submissions to the Speech Translation evaluation campaign at IWSLT2018. Our end-to-end speech translation systems are based on ESPnet and implements an attention-based encoder-decoder model. As comparison, we also experiment with a pipeline system that uses independent neural network systems for both the speech transcription and text translation components. We find that a transfer learning approach that bootstraps the end-to-end speech translation system with speech transcription system’s parameters is important for training on small datasets.
🌉
Interdisciplinary Bridge
— Artificial Intelligence and Deep Learning and Natural Language Processing and Speech & Audio
🧭
Keyword Pioneer
— pipeline system
🐣
Hot Topic Early Bird
— speech translation
🐝
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
Artificial Intelligence > Core AI > Multimodal Learning
Artificial Intelligence > Learning Paradigms > Transfer Learning
Deep Learning > Architectures > Transformers
Natural Language Processing > Applications > Machine Translation
Speech & Audio > Recognition > Automatic Speech Recognition
Deep Learning > Learning Types > Transfer Learning
Speech & Audio > Recognition > Speech Translation