13-14 July, 2023 - Toronto
The International Conference on Spoken Language Translation (IWSLT) is an annual scientific conference, associated with an open evaluation campaign on spoken language translation, where both scientific papers and system descriptions are presented.
The 20th edition of IWSLT will be co-located with ACL 2023 in Toronto, Canada on 13-14 July, 2023, and run as a hybrid event.
Program at a Glance
IWSLT 2023 will occur on two days, 13-14 July, as a hybrid event in-person and online.
Please find here the detailed program.
To be announced shortly.
The IWSLT 2023 Evaluation Campaign will host shared tasks featuring the following focus areas:
- Speech translation of talks:
- Offline track (Marco Turchi, Zoom, Germany, Matteo Negri, FBK, Italy)
- Simultaneous track (Xutai Ma, Juan Pino, Meta; Katsuhito Sudoh, NAIST, Japan)
- Subtitling track (Mauro Cettolo, FBK, Italy; Evgeny Matusov, AppTek, Germany)
- Multilingual track: ACL 60-60 initiative (Elizabeth Salesky, JHU; Jan Niehues, KIT)
- Speech-to-speech translation of multi-source data:
- Speech-to-speech track (Qianqian Dong, Tom Ko, Mingxuan Wang, Bytedance, China)
- Speech dubbing of multi-source data:
- Dubbing track (Prashant Mathur, Brian Thompson, AWS AI Labs, USA)
- Dialectal and Low-resource speech translation:
- Dialectal and low-resource tracks (Multi-organizer collaboration)
- Formality control for SLT:
- Formality track (Benjamin Hsu, AWS AI Labs; Marine Carpuat, UMD)
Data, metrics, and evaluation will be provided by the conference organizers.
All tasks will follow the same important dates.
Please register for the Evaluation Campaign via the registration form.
Please join the IWSLT Evaluation Campaign google group for periodic updates, community questions and opportunities to receive sponsored cloud computing credits.
Submissions should be scientific papers or system papers. All papers may consist of 4 to 8 pages of content with additional pages of references, formatted using the ACL stylesheets. Upon acceptance, all papers will be given one (1) additional content page to address reviewers’ comments. Accepted papers will be published in the ACL 2023 proceedings and will be presented at the IWSLT conference either orally or as a poster.
Please submit scientific papers and system papers through the submission portal.
- Scientific papers must be anonymized for submission, while system description papers do not need to be.
- We accept submissions which have previously been made available as technical reports or preprints, e.g. on arXiv.
- We will not accept scientific papers for publication that overlap significantly in content or results with papers published elsewhere.
- Scientific papers which have been, or plan to be, submitted to other venues must be declared as such at the time of submission, and must be withdrawn from the other venues if accepted and published at IWSLT 2023.
- Scientific papers whose first author is a student will be eligible for the IWSLT 2023 Best Student Paper Award (authors should note eligibility in the paper submission form).
- Limitations and Ethics Statement sections (see the ACL23 call for papers for more details) are encouraged but not required. If included, they should be placed after the conclusion for submission and will not count against the page limit.
|Jan 14, 2023||Release of shared task training and dev data|
|Apr 1-18, 2023||Evaluation period|
|Apr 24, 2023||Paper submission deadline (all papers)|
|May 2, 2023||System papers update deadline|
|May 22, 2023||Notification of acceptance|
|May 31, 2023||Camera ready paper due|
|July 12, 2023||Pre-recorded video due|
|July 13-14, 2023||IWSLT conference|
Note: All deadlines are 11:59PM UTC-12:00.
- Marine Carpuat, University of Maryland, USA (Program Chair)
- Marcello Federico, AWS AI Labs, USA (Conference Chair)
- Alex Waibel, CMU, USA (Conference Chair)
- Jan Niehues, KIT, Germany (Evaluation Chair)
- Sebastian Stüker, KIT, Germany (Sponsorship Chair)
- Elizabeth Salesky, JHU, USA (Publication and Website Chair)
- Atul Kr. Ojha, University of Galway, Ireland (Publicity Chair)
- Sweta Agrawal, University of Maryland
- Duygu Ataman, New York University
- Laurent Besacier, Naver Labs
- Roldano Cattoni, Fondazione Bruno Kessler
- Alexandra Chronopoulou, LMU Munich
- Josep Maria Crego, Systran
- Mattia Di Gangi, AppTek
- Qianqian Dong, ByteDance AI Lab
- Akiko Eriguchi, Microsoft
- Carlos Escolano, Polytechnic University of Catalonia
- Markus Freitag, Google
- Hirofumi Inaguma, Meta AI
- Tom Ko, ByteDance AI Lab
- Surafel M. Lakew, Amazon AI
- Yves Lepage, Waseda University
- Xutai Ma, Meta AI
- Wolfgang Macherey, Google
- Prashant Mathur, Amazon AI
- Evgeny Matusov, AppTek
- Kenton Murray, Johns Hopkins University
- Maria Nadejde, Amazon Web Services
- Matteo Negri, Fondazione Bruno Kessler
- Xing Niu, Amazon AI
- Raghavendra Reddy Pappagari, Johns Hopkins University
- Juan Pino, Meta
- Elijah Rippeth, University of Maryland
- Elizabeth Salesky, Johns Hopkins University
- Rico Sennrich, University of Zurich
- Matthias Sperber, Apple
- Sebastian Stüker, Zoom
- Katsuhito Sudoh, Nara Institute of Science and Technology
- Brian Thompson, Amazon AWS AI
- Marco Turchi, Zoom
- David Vilar, Google
- Changhan Wang, Meta AI
- Krzysztof Wolk, Polish-Japanese Institute of Information Technology
IWSLT welcomes sponsorships!