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.
Cite
CITATION STYLE
Xinyuan, H. L., Verma, N., Odoom, B. B., Pradeep, U., Wiesner, M., & Khudanpur, S. (2023). JHU IWSLT 2023 Multilingual Speech Translation System Description. In 20th International Conference on Spoken Language Translation, IWSLT 2023 - Proceedings of the Conference (pp. 302–310). Association for Computational Linguistics. https://doi.org/10.18653/v1/2023.iwslt-1.28
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
