Improving End-to-End Speech Translation by Imitation-Based Knowledge Distillation with Synthetic Transcripts
Open Access
- 1 January 2023
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 89-101
Abstract
Rebekka Hubert, Artem Sokolov, Stefan Riezler. Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023). 2023.Keywords
All Related Versions
This publication has 22 references indexed in Scilit:
- BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech RecognitionIEEE Journal of Selected Topics in Signal Processing, 2022
- A General Multi-Task Learning Framework to Leverage Text Data for Speech to Text Tasks2021
- Europarl-ST: A Multilingual Corpus for Speech Translation of Parliamentary Debates2020
- Autoregressive Knowledge Distillation through Imitation Learning2020
- On Exposure Bias, Hallucination and Domain Shift in Neural Machine Translation2020
- A Comparative Study on End-to-End Speech to Text Translation2019
- Leveraging Weakly Supervised Data to Improve End-to-end Speech-to-text Translation2019
- End-to-End Automatic Speech Translation of Audiobooks2018
- Rethinking the Inception Architecture for Computer Vision2016
- A Learning Algorithm for Continually Running Fully Recurrent Neural NetworksNeural Computation, 1989