We describe our experience with providing automatic simultaneous spoken language translation for an event with human interpreters. We provide a detailed overview of the systems we use, focusing on their interconnection and the issues it brings. We present our tools to monitor the pipeline and a web application to present the results of our SLT pipeline to the end users. Finally, we discuss various challenges we encountered, their possible solutions and we suggest improvements for future deployments.
Ondřej Bojar, Vojtěch Srdečný, Rishu Kumar, Otakar Smrž, Felix Schneider, Barry Haddow, Phil Williams, and Chiara Canton. 2021.Operating a Complex SLT System with Speakers and Human Interpreters. InProceedings of the 1st Workshop on Automatic Spoken Language Translation in Real-World Settings (ASLTRW), pages 23–34, Virtual. Association for Machine Translation in the Americas.
@inproceedings{bojar-etal-2021-operating, title = "Operating a Complex {SLT} System with Speakers and Human Interpreters", author = "Bojar, Ond{\v{r}}ej and Srde{\v{c}}n{\'y}, Vojt{\v{e}}ch and Kumar, Rishu and Smr{\v{z}}, Otakar and Schneider, Felix and Haddow, Barry and Williams, Phil and Canton, Chiara", editor = "Turchi, Marco and Fantinuoli, Claudio", booktitle = "Proceedings of the 1st Workshop on Automatic Spoken Language Translation in Real-World Settings (ASLTRW)", month = aug, year = "2021", address = "Virtual", publisher = "Association for Machine Translation in the Americas", url = "https://aclanthology.org/2021.mtsummit-asltrw.3/", pages = "23--34", abstract = "We describe our experience with providing automatic simultaneous spoken language translation for an event with human interpreters. We provide a detailed overview of the systems we use, focusing on their interconnection and the issues it brings. We present our tools to monitor the pipeline and a web application to present the results of our SLT pipeline to the end users. Finally, we discuss various challenges we encountered, their possible solutions and we suggest improvements for future deployments."}
%0 Conference Proceedings%T Operating a Complex SLT System with Speakers and Human Interpreters%A Bojar, Ondřej%A Srdečný, Vojtěch%A Kumar, Rishu%A Smrž, Otakar%A Schneider, Felix%A Haddow, Barry%A Williams, Phil%A Canton, Chiara%Y Turchi, Marco%Y Fantinuoli, Claudio%S Proceedings of the 1st Workshop on Automatic Spoken Language Translation in Real-World Settings (ASLTRW)%D 2021%8 August%I Association for Machine Translation in the Americas%C Virtual%F bojar-etal-2021-operating%X We describe our experience with providing automatic simultaneous spoken language translation for an event with human interpreters. We provide a detailed overview of the systems we use, focusing on their interconnection and the issues it brings. We present our tools to monitor the pipeline and a web application to present the results of our SLT pipeline to the end users. Finally, we discuss various challenges we encountered, their possible solutions and we suggest improvements for future deployments.%U https://aclanthology.org/2021.mtsummit-asltrw.3/%P 23-34
Ondřej Bojar, Vojtěch Srdečný, Rishu Kumar, Otakar Smrž, Felix Schneider, Barry Haddow, Phil Williams, and Chiara Canton. 2021.Operating a Complex SLT System with Speakers and Human Interpreters. InProceedings of the 1st Workshop on Automatic Spoken Language Translation in Real-World Settings (ASLTRW), pages 23–34, Virtual. Association for Machine Translation in the Americas.