Do you have a fully reviewed ARR paper related to speech translation that you'd like to commit to IWSLT 2025?
IWSLT has enabled paper commitment for fully reviewed papers from ARR for 2025.
If you'd like to commit your paper, please fill out this form by *May 17th, 2025*:
forms.gle/1QtVrHXyCGoE...
🗓️ Deadline update 🗓️
To accommodate requests, we have extended the test period for *all tasks* until *April 19th.*
System description papers are now due *April 24th.*
Thank you and good luck to all participants!!
The evaluation period has begun for our shared tasks!
The test data is now available on our website, and submissions are due Tuesday April 15! ⏰
Please email task organizers or the google group with any questions 🥳
✨ IWSLT paper submission deadline update ✨
Paper submission deadline:
🗓️ March 22, 2025
🔗 SoftConf portal: softconf.com/acl2025/iwsl...
For more details, see: iwslt.org/2025/#paper-...
Call for Demos 🗣️🤖💻
For 2025, we invite interactive system demonstrations for a session highlighting innovative systems, tools, and component technologies that advance the field of speech translation.
For more info, see our call below!
🗓️: Deadline Apr 25
🔗: iwslt.org/2025/call-fo...
Why participate?
🔓 Help make the world’s vast audiovisual heritage accessible to all!
🔍 Join the scientific effort to push forward multilingual subtitling and improve global communication! 🌎
#SpeechTranslation #AIforGood
🆕 For this year, Arabic joins the challenge!
✨ For the first time, we ask participants to generate subtitles for Arabic, covering the 5th most spoken language and one of the six UN 🌐 official languages.
Let’s break language barriers! 🌍
#Subtitling #IWSLT2025
Our last task: Subtitling!!
🎯 Goal: The IWSLT 2025 Subtitling Track challenges participants to generate accurate Arabic & German subtitles for English audiovisual recordings, bridging language gaps in media! 🌍📺
#AI #SpeechTech #Subtitling #IWSLT2025
🔗: iwslt.org/2025/subtitl...
Why participate?
✨ Contribute to advancing real-world systems for multilingual speech translation, particularly for underrepresented languages
✨ Collaborate to bridge linguistic divides & make this technology more accessible to millions of speakers worldwide
For the 2nd iteration...
🆕 Significantly more data for low-resource Indic languages + more language directions!
➡️ Both English to Indic and Indic to English translation directions, addressing the unique challenges posed by low-resource linguistic contexts.
Our final task highlight: Indic speech translation!
🎯 Goal: develop a speech-to-text translation model that bridges the gap for low-resource Indian languages, focusing on Hindi, Bengali, and Tamil from the Indo-Aryan and Dravidian families.
🔗: iwslt.org/2025/indic
Why participate?
✨Low-resource is truly the frontier, and there are many ways to making an impact for a language community:
from providing a dataset for a language that is missing one, to exploring the limits of different models and techniques.
🆕 This year includes new and more diverse language pairs (e.g. Fongbe to French, Estonian to English) in addition to continuing pairs
🆕🔊 Also new this year is a *data track* which encourages the creation of new speech translation datasets for less-supported languages
Today's task: Low-resource ST!
🎯 Goal: Building speech translation models for currently underserved, mostly low-resource languages and varieties
🗓️ This is the 5th iteration, with new and continuing language pairs (10 total!)
🔗: iwslt.org/2025/low-res...
Why participate?
🚀 - An #IWSLT tradition: the perfect arena to set the state-of-the-art in Spoken Language Translation, test new solutions, join an active research community & push AI’s limits to transform global communication! 🌍🎙️🤖
What is new and different this year?
✨🆕 – The challenge gets tougher! Participants will engage with Arabic as a new target language (alongside German & Chinese) 🌍 and diverse testing scenarios featuring unique speech styles, accents & recording conditions.
🎤 Are you ready?
Today's task is an IWSLT mainstay: Offline ST!
🎯 Goal – Provide a stable & shared evaluation framework to track advances in Spoken Language Translation from English into multiple languages & domains. 🌍🎙️
#AI #SpeechTech #SpeechTranslation #IWSLT2025
🆕: This year focuses on realistic use - unsegmented long-form speech. Participants are allowed to use public LLMs for sophisticated ST with long contexts for long-form speech.
Why participate? This is the first shared task for truly realistic, long-form speech!
Next up: simultaneous speech translation!
🎯 Goal: to explore ways to translate speech into another language like simultaneous interpreting.
🔗 Link: iwslt.org/2025/simulta...
Why participate?
⚠️ Urgent, ⏰ timely, and 💪 challenging for those passionate about speech technology 🗣️ and sustainable AI 🌍
Don’t miss out! #SpeechTech #SustainableAI
Today's task: model compression!!
🆕 New at IWSLT! But no less exciting 🔥
🎯 Goal: Compress a large, general-purpose multimodal model, making speech translation more efficient ⚡️, deployable 📲, and sustainable ♻️, while preserving translation quality ⭐️
#AI #SpeechTech #ModelCompression #LLMcompression
Why participate?
Collectively explore this new task paradigm!
This task provides an opportunity to compete with flexibility to leverage any model and within constrained, controllable settings, fostering research advancements and reliable findings. Together, we will learn more!
First up, a new task for 2025:
*Instruction-following for speech processing!*
Explore instruction-following for speech ⇨
Integrate speech foundation models with LLMs across tasks such as speech translation, recognition, summarization, and QA.
🔗: iwslt.org/2025/instruc...
We are pleased to announce that our 2025 shared tasks have launched! Find details and data on our website, with evaluation data to be released April 1!
iwslt.org/2025/#shared...
We will be highlighting one task per day here and the other site. Join us for an exciting year of speech translation!!
