Meetween is an EU-funded project building ethical, inclusive, human-centred video tech. #Meetween #AIForGood
Joined January 2024
- Tweets 55
- Following 21
- Followers 76
- Likes 11
15 Photos and videos
May 29
If you work in the language industry and are in Rome, you can't miss the ๐๐๐ฌ๐ฌ๐ข๐ฏ๐๐ฅ๐ฒ ๐๐ฎ๐ฅ๐ญ๐ข๐ฅ๐ข๐ง๐ ๐ฎ๐๐ฅ ๐๐ ๐๐จ๐ง๐๐๐ซ๐๐ง๐๐ ๐๐๐๐, organised by our partner TAUS to celebrate European translation technology. Come and meet us!๐
May 28
๐ ๐๐ข ๐๐๐ก๐จ๐จ๐ฅ ๐ฉ๐ซ๐๐ฌ๐๐ง๐ญ๐ฌ ๐๐๐๐ญ๐ฐ๐๐๐ง ๐๐ญ ๐๐๐๐ ๐๐๐๐
๐๐ก๐๐ญ ๐ข๐ ๐ฒ๐จ๐ฎ ๐๐จ๐ฎ๐ฅ๐ ๐ฌ๐๐ง๐ ๐ ๐๐ข๐ ๐ข๐ญ๐๐ฅ ๐๐ฏ๐๐ญ๐๐ซ ๐ญ๐จ ๐ฒ๐จ๐ฎ๐ซ ๐ง๐๐ฑ๐ญ ๐๐๐ฅ๐ฅ?
That's not a hypothetical. It's what the Meetween project is building.
On 5 June, Pi School's Managing Director Sรฉbastien Bratiรจres will take the stage at the TAUS Massively Multilingual AI Conference in Rome to present Meetween, the EU Horizon Europe project developing technology for multilingual, multimodal AI-powered meetings, where language and culture no longer become barriers.
The consortium behind Meetween includes Academic Computer Centre CYFRONET AGH, Fondazione Bruno Kessler - FBK, ฤฐstanbul Teknik รniversitesi, Karlsruher Institut fรผr Technologie (KIT), Zoom, Translated, and TAUS, the organiser of the event.
๐ Rome | 5 June, 11:15 | Day 2
๐
๐จ๐ฅ๐ฅ๐จ๐ฐ @MeetweenEU on LinkedIn and X and visit ๐ย pischool.link/Meetween
#Meetween #TAUS2026 #MultilingualAI #MachineTranslation #EUHorizon #ArtificialIntelligence #NLP #HorizonEurope
1
21
May 8
Many languages are left behind by AI translation. Not for lack of need, but lack of data. Meetween is closing that gap. See us at #TAUS2026 in Rome, 3โ5 June. #Meetween #MultilingualAI
1
2
5
96
Apr 30
๐๐จ๐ฆ๐ ๐๐ง๐ ๐ฆ๐๐๐ญ #๐๐๐๐ญ๐ฐ๐๐๐ง ๐๐ญ ๐๐๐๐ ๐๐๐๐! Two @FBK_research papers accepted. Palma de Mallorca, 11โ16 May.
#LREC2026
1
5
129
Apr 20
Two Meetween papers at #LREC2026 by @MaikeZufle, PhD researcher in instruction-following speech models and full-duplex dialogue at the Karlsruher Institut fรผr Technologie (KIT).
๐ MuSaG
๐ Talk2Ref
๐ lrec2026.info/
#Meetween #NLP
2
5
134
Apr 10
4 papers accepted at #LREC -COLING 2026 in Palma de Mallorca ๐
Sarcasm detection, reference prediction, gender bias in speech translation, and low-resource ASR.
Meet the team, 11โ16 May 2026 ๐ lrec2026.info/
Follow us for paper deep-dives in the coming weeks.
#NLP
2
8
147
Apr 1
Meetween is part of the organising committee of #IWSLT2026 โ the premier conference on spoken language translation. The Shared Task Evaluation Period is open. Working on #speechtranslation, instruction following, or #modelcompression?
Get involved now! ๐ iwslt.org/2026
4
4
139
Mar 26
๐๏ธ Our paper on connecting Speech Foundation Models with LLMs is featured in the SpeechLMM Training Journal on Weights & Biases.
Read it ๐ bit.ly/4svG7ll
SpeechLMM 2.0 coming this summer. ๐
#Meetween #SpeechLMM #AI #NLP
1
4
137
Mar 19
๐๏ธ Two people. Two languages. One conversation!ย
No delays. No switching languages. No one is left out.
This is what we are building.
#SpeechAI #MultilingualAI #HorizonEurope
1
4
143
Feb 26
Meetween Butler enables real-time speech-to-speech translation while preserving voice and tone, plus automatic notes and smart summaries.
Built on ๐จ๐ฉ๐๐ง-๐ฌ๐จ๐ฎ๐ซ๐๐, ๐ฉ๐ซ๐ข๐ฏ๐๐๐ฒ-๐๐ฐ๐๐ซ๐ and ๐ซ๐๐ฌ๐ฉ๐จ๐ง๐ฌ๐ข๐๐ฅ๐ ๐๐ฒ ๐๐๐ฌ๐ข๐ ๐ง.
#Meetween #ResponsibleAI
1
2
60
Meetween retweeted
๐ข Postdoc Opening in Multimodal AI
Iโm looking for a postdoc to join my lab at @itu1773 for our EU-funded @MeetweenEU project. Youโd be working in a collaborative team with kind, smart, and hard-working people.
Please feel free to share with anyone who might be interested.
4
13
1,547
Feb 20
#Mumospee Dataset v2 is out.
645,000 hours of multilingual, multimodal meeting data, including 84,000 new audiovisual hours, powering #SpeechLLMs, speech-to-speech translation and vision-based AI.
Explore: bit.ly/4qIu8PC
#Meetween #SpeechAI #MultilingualAI
2
35
Feb 10
Meetings where language isnโt a barrier and no insights are missed.
๐๐ฎ๐ญ๐ฅ๐๐ซ ๐๐ฒ #๐๐๐๐ญ๐ฐ๐๐๐ง will ๐ญ๐ซ๐๐ง๐ฌ๐ฅ๐๐ญ๐, ๐ญ๐๐ค๐ ๐ง๐จ๐ญ๐๐ฌ, and ๐ฌ๐ฎ๐ฆ๐ฆ๐๐ซ๐ข๐ฌ๐ ๐ฆ๐๐๐ญ๐ข๐ง๐ ๐ฌ ๐ข๐ง ๐ซ๐๐๐ฅ ๐ญ๐ข๐ฆ๐, all within your video calls. Clearer focus. Better conversations.
1
3
156
Jan 29
The Meetween consortium met in Rome for a two-day in-person session hosted by @Translation and @picampusschool.
Partners aligned on SpeechLMM progress, roadmap, ethics and next steps toward open, trustworthy speech foundation models.
#Meetween #EuropeanAI #OpenSourceAI
2
6
296
Jan 22
Two years in, Meetween is transforming how we meet.
โ
SpeechLMM v1 released
โ
560k hrs of multilingual speech shared
โ
Global AI benchmarks ethical design
โ
Built with real users
The future of meetings is here, and it's inclusive.
#Meetween #AIForGood
2
3
93
Jan 13
Online meetings connect people.
They also add friction. Language. Time zones. Tools.
Meetween is an EU-funded project exploring how AI can support natural and inclusive online collaboration. People first. Real conversations.
Discover more: bit.ly/Meetween
#Meetween #AI
2
4
83
Meetween retweeted
1 Dec 2025
IMTalker: Efficient Audio-driven Talking Face Generation with Implicit Motion Transfer
TLDR: A motion transfer model, similar to LivePortrait, which replaces the typical warping paradigm with a cross attention model that implicitly learns motion.
๐ฝ๏ธ Project Page: cbsjtu01.github.io/IMTalker/
๐ Paper: arxiv.org/pdf/2511.22167
๐ป Code: github.com/cbsjtu01/IMTalker
2
22
105
7,468
24 Sep 2025
๐ Meet FAMA: a ๐ฎ๐น Italian ๐ฌ๐ง English Speech Foundation Model, built in the MEETWEEN project under the #OpenScience framework!
๐ Check it out: arxiv.org/pdf/2505.22759
๐ Excited to present FAMA, the first large-scale #OpenScience #Speech foundation model for ๐ฎ๐น Italian & ๐ฌ๐ง English, at #clicit2025 (17:30โ18:45 oral session)!
๐ Models: hf.co/collections/FBK-MT/famโฆ
๐ Data: hf.co/datasets/FBK-MT/fama-dโฆ
๐ป Code: github.com/hlt-mt/FBK-fairseโฆ
#SpeechTech
2
2
447
13 Jun 2025
Weekly pick from the #MeetweenScientificWatch: Overtrained language models are harder to fine-tune โ This study reveals how longer pretraining can harm downstream adaptability, introducing "catastrophic overtraining" as a real risk. ๐ง ๐
arxiv.org/abs/2503.19206
1
121
๐ข The evaluation period of the Instruction Following task at @iwslt 2025 just started!
๐ฅ๏ธ Consider submitting your speech-to-text system!
The outputs can be easily uploaded on the SPEECHM platform developed in the @MeetweenEU project!
โก๏ธ iwslt2025.speechm.cloud.cyfrโฆ
9
16
697
5 Mar 2025
Weekly pick from the #MeetweenScientificWatch: โThe Ultra-Scale Playbook: Training LLMs on GPU Clustersโ โ A deep dive into scaling LLM training from 1 to 1000 GPUs, demystifying parallelism techniques with practical examples. ๐๐ฅ๏ธ๐ huggingface.co/spaces/nanotrโฆ
2
2
143