So happy to announce that our paper 'Enhancing Gender-Inclusive Machine Translation with Neomorphemes and Large Language Models' has been accepted at EAMT2024! 🎉 Amazing co-authors: BeatriceSavoldi Matteo Negri Luisa Bentivogli See you in Sheffield! 🧐 #MT #AI #EAMT EAMT

📢 Proud to announce that our Marco Gaido has won the 2023 EAMT best Phd thesis award with his work on “Direct speech translation toward high-quality, inclusive, and augmented systems". 💯👏 👇Thesis: iris.unitn.it/handle/11572/3… 👇About the award: eamt.org/2024/04/17/202… #NLProc

Interesting study on the encoding of tones in pre-trained speech models: arxiv.org/abs/2403.16865 Suprasegmental cues contribute to making speech complex and fascinating. Considering them when interpreting the inner workings of speech models could provide useful insights. MT Group at FBK

🐾 Do you wanna see a Hyena in action? 🐾 🥁 Tomorrow Marco Gaido will present the paper "How do Hyenas deal with Human Speech? Speech Recognition and Translation with ConfHyena" at LREC COLING 2024! ⏲️ Poster session 1: 11:00-12:40 🦴 See you there! #NLProc #LRECCOLING2024 #ASR #ST

Our pick of the week by Marco Gaido: "Risks and Opportunities of Open-Source Generative AI" by Francisco Girbal Eiras, Christian Schroeder de Witt, Adel Bibi, Botos Csabi, Fabro Steibel, Fazel Keshtkar, Fazl Barez, Jordi Cabot, Lori Landay, et al., 2024. #open #opensource #generative #generativeai #genai #ai

Interested in automatic subtitling? Want to know more about benefits and challenges? Don't miss the interview to our Mauro Cettolo for the AI4Culture series "Close Encounters with AI" #nlproc

In Sheffield for #EAMT2024! Ready to present our research and engage with this amazing community Luisa Bentivogli BeatriceSavoldi Marco Gaido Andrea Piergentili EAMT2024

📢Tomorrow morning at 10:45 our very own Marco Gaido will receive the #EAMT2024 best thesis award! 👏Come listen to the presentation of his amazing research on direct speech translation: toward high-quality, inclusive, and augmented systems! Marco Gaido Fondazione Bruno Kessler - FBK #nlproc

Marco Gaido from MT Group at FBK presenting his PhD work @ #EAMT2024 Marco is the winner of the Anthony C Clarke EAMT Best Thesis Award #NLProc #MT

Interested in how to enhance gender-inclusive #machinetranslation with LLMs? Come to #eamt2024 poster session at 13:45 and talk to our PhD student Andrea Piergentili! 📌Paper: arxiv.org/pdf/2405.08477 EAMT2024 BeatriceSavoldi Matteo Negri Luisa Bentivogli

📢Come and join our group! We offer a fully funded 3-year PhD position with the IECS Doctorate School Università di Trento: Speech Translation in the LLM Era (Area A6) ⏱️Deadline: August 5th, 2024, h 4.00pm (CEST) 📌Application Details: iecs.unitn.it/education/admi… #NLProc Fondazione Bruno Kessler - FBK

Interesting hints from ieeexplore.ieee.org/stamp/stamp.js… on the capability of speech models to encode articulatory phenomena below the phone level. A good example of fine-grained phonetic explainability, accompanied by a nice visualizer tool! MT Group at FBK

Wonderful poster session this evening at #ACL2024NLP 🐘 Want to know more about this work on simultaneous speech translation from unbounded speech? 👉🏼 Look here: arxiv.org/abs/2406.06097 #NLProc #ACL2024 #speech

What a poster session this morning at #ACL2024NLP ⚡️⚡️ Marco Gaido here was presenting SBAAM: Eliminating transcript dependency in automatic subtitling More info here: arxiv.org/abs/2405.10741 #NLProc #ACL2024 #subtitling #speech

🎉Great news! Our paper “Speech Translation with Speech Foundation Models and Large Language Models: What is There and What is Missing?” got the outstanding paper & area chair's awards!!! 👏 👇arxiv.org/pdf/2402.12025 #NLProc #ACL2024NLP

Super honoured to receive both Outstanding paper and Senior Area Chairs Award from #ACL2024NLP for our survey (authored by Marco Gaido, me, Matteo Negri, Luisa Bentivogli) on the emerging paradigm of speech foundation models + LLM for speech translation! 👉🏼arxiv.org/abs/2402.12025

Our Beomseok LEE @ INTERSPEECH 🇬🇷 presenting "Speech-MASSIVE: A Multilingual Speech Dataset for SLU and Beyond" at #INTERSPEECH2024 🇬🇷 Check here for more details: arxiv.org/abs/2408.03900

Today, at the DigitalIndustry-FBK Demo Day, Andrea Piergentili introduced our tool for Gender Neutral Translation with #LLMs. @fbk_research #NLProc