JHU IWSLT 2023 Multilingual Speech Translation System Description

Henry Li Xinyuan, Neha Verma, Bismarck Bamfo Odoom, Ujvala Pradeep, Matthew Wiesner, Sanjeev Khudanpur


Abstract
We describe the Johns Hopkins ACL 60-60 Speech Translation systems submitted to the IWSLT 2023 Multilingual track, where we were tasked to translate ACL presentations from English into 10 languages. We developed cascaded speech translation systems for both the constrained and unconstrained subtracks. Our systems make use of pre-trained models as well as domain-specific corpora for this highly technical evaluation-only task. We find that the specific technical domain which ACL presentations fall into presents a unique challenge for both ASR and MT, and we present an error analysis and an ACL-specific corpus we produced to enable further work in this area.
Anthology ID:
2023.iwslt-1.28
Volume:
Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023)
Month:
July
Year:
2023
Address:
Toronto, Canada (in-person and online)
Editors:
Elizabeth Salesky, Marcello Federico, Marine Carpuat
Venue:
IWSLT
SIG:
SIGSLT
Publisher:
Association for Computational Linguistics
Note:
Pages:
302–310
Language:
URL:
https://aclanthology.org/2023.iwslt-1.28
DOI:
10.18653/v1/2023.iwslt-1.28
Bibkey:
Cite (ACL):
Henry Li Xinyuan, Neha Verma, Bismarck Bamfo Odoom, Ujvala Pradeep, Matthew Wiesner, and Sanjeev Khudanpur. 2023. JHU IWSLT 2023 Multilingual Speech Translation System Description. In Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023), pages 302–310, Toronto, Canada (in-person and online). Association for Computational Linguistics.
Cite (Informal):
JHU IWSLT 2023 Multilingual Speech Translation System Description (Xinyuan et al., IWSLT 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.iwslt-1.28.pdf