IWSLT
@iwslt.bsky.social
The International Conference on Spoken Language Translation & SIGSLT.
Join us for the 22nd edition of IWSLT on 31 July-1 Aug 2025, co-located with ACL! See more at https://iwslt.org/
Join us for the 22nd edition of IWSLT on 31 July-1 Aug 2025, co-located with ACL! See more at https://iwslt.org/
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
🔓 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
February 5, 2025 at 4:52 PM
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
🔓 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
✨ 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
February 5, 2025 at 4:52 PM
🆕 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
✨ 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
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
✨ 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
February 4, 2025 at 8:05 PM
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
✨ 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.
🆕 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.
February 4, 2025 at 8:05 PM
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.
🆕 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.
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.
✨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.
February 3, 2025 at 5:32 PM
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.
✨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
🆕🔊 Also new this year is a *data track* which encourages the creation of new speech translation datasets for less-supported languages
February 3, 2025 at 5:32 PM
🆕 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
🆕🔊 Also new this year is a *data track* which encourages the creation of new speech translation datasets for less-supported languages
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! 🌍🎙️🤖
🚀 - 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! 🌍🎙️🤖
January 31, 2025 at 5:32 PM
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! 🌍🎙️🤖
🚀 - 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?
✨🆕 – 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?
January 31, 2025 at 5:32 PM
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?
✨🆕 – 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?
🆕: 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!
Why participate? This is the first shared task for truly realistic, long-form speech!
January 30, 2025 at 7:31 PM
🆕: 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!
Why participate? This is the first shared task for truly realistic, long-form speech!
Why participate?
⚠️ Urgent, ⏰ timely, and 💪 challenging for those passionate about speech technology 🗣️ and sustainable AI 🌍
Don’t miss out! #SpeechTech #SustainableAI
⚠️ Urgent, ⏰ timely, and 💪 challenging for those passionate about speech technology 🗣️ and sustainable AI 🌍
Don’t miss out! #SpeechTech #SustainableAI
January 29, 2025 at 4:47 PM
Why participate?
⚠️ Urgent, ⏰ timely, and 💪 challenging for those passionate about speech technology 🗣️ and sustainable AI 🌍
Don’t miss out! #SpeechTech #SustainableAI
⚠️ Urgent, ⏰ timely, and 💪 challenging for those passionate about speech technology 🗣️ and sustainable AI 🌍
Don’t miss out! #SpeechTech #SustainableAI
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!
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!
January 28, 2025 at 6:13 PM
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!
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!