🌟 Introducing Llama-AVSR, a multimodal LLM with strong audio-visual speech recognition capabilities. New sota on the LRS3 dataset for the tasks of AVSR and ASR, and sota for VSR. Work done at Imperial College London in collaboration with AI at Meta. 📜 Link: arxiv.org/abs/2409.12319

🚀 New IWSLT shared task on model compression: shrink a large multimodal model while preserving speech translation quality. Are you in? 🌍 Smaller is greener! #IWSLT2025 #NLP #SpeechTech #SustainableAI iwslt.org/2025/model-com…

If you are working on learning-based approaches for (multiple) sound source localization and tracking, keep in mind our special session at EUSIPCO2025 . Submission deadline: March 1st Track: 20.6 Submission link: eusipco2025.org/submit-your-pa…

Le nuove frontiere dell’AI nelle tecnologie del linguaggio L’Eu punta su tecnologie del linguaggio etiche e inclusive per preservare multilinguismo e diversità culturale con il consorzio ALT-EDIC, di cui FBK è partner bit.ly/3EIfo0Z

The Speerch Technology Lab grows bringing in fresh energy from two new young talents. Prachi Sharma and Lorenzo Concina will advance our tools for speech and language technologies, contributing to ELOQUENCE AI. Meetween and the ALT-EDIC projects.

On the red carpet on my way to attend the Assembly of Members of the Alliance for Language Technology #ALTEDIC and the kick off of the LLMs4EU project: towards preserving our cultural and language diversity and giving european citizens open and ethical #languagetechnologies

🚀 New tech report out! Meet FAMA, our open-science speech foundation model family for both ASR and ST in 🇬🇧 English and 🇮🇹 Italian. The models are live and ready to try on Hugging Face 👇 🔗 huggingface.co/collections/FB… #ASR #ST #OpenScience #MultilingualAI

FAMA è il primo foundation model vocale open-science per ita e eng, sviluppato da FBK. Riconosce e traduce la voce usando solo dati e strumenti pubblici: oltre 150.000 ore di audio open, codice e processi completamente accessibili. fbk_stek MT Group at FBK magazine.fbk.eu/it/news/la-pri…

We have an open position on resource-aware and dynamic speech processing within the IPCEI-CIS project. It is about cutting edge ML applied to speech processing. It will be fun. Details:shorturl.at/E4DXR DM me for any request. #ASR #speechprocessing #AI #ML Fondazione Bruno Kessler - FBK

The SpeechTek lab is at #Interspeech2025 with several papers . Do not miss: - seraphina on ASR-LLM in low-resourced lang. - Abdul Hannan on efficient ASR - Darline Marx on speech disorderds in kids - Umberto Cappellazzo on ACSR - Our contributio to Granary See you around.

We got IDs of papers submitted to ICASSP above 14K....🙃

🚀 Excited to present FAMA, the first large-scale #OpenScience #Speech foundation model for 🇮🇹 Italian & 🇬🇧 English, at #clicit2025 (17:30–18:45 oral session)! 🔗 Models: hf.co/collections/FB… 📊 Data: hf.co/datasets/FBK-M… 💻 Code: github.com/hlt-mt/FBK-fai… #SpeechTech

🔊 Meet FAMA: a 🇮🇹 Italian + 🇬🇧 English Speech Foundation Model, built in the MEETWEEN project under the #OpenScience framework! 👉 Check it out: arxiv.org/pdf/2505.22759

🚀 Join us for the LT@FBK day 2025! Discover cutting-edge research and highlights in speech and language technologies from Fondazione Bruno Kessler - FBK 📅 October 28, 2025 📍 FBK, Trento Details and registration: fbk.eu/en/event/34674…

LT@FBK 2025: l'evento dedicato alle Language Technologies - con 16 talk, 13 poster e una keynote d'eccezione - ha offerto un ampia panoramica a ricercatrici e ricercatori impegnati nello sviluppo di tecnologie per il linguaggio e la comunicazione. magazine.fbk.eu/it/news/ltfbk-…

Our Lorenzo Concina and seraphina in action, explaining very quickly what we are doing for multilingual ASR and low resourced languages within ELOQUENCE AI huggingface.co/SpeechTek/MEUS… Fondazione Bruno Kessler - FBK #MultilignualASR #ASR @LLM

Within the wildbotics.eu MSCA we are hiring 1 PhD student on "AI-based soundscape analysis". More details here: wildbotics.eu/recruitment Deadline on Jan 7th Fondazione Bruno Kessler - FBK

Our call for PhD candidates within the MSCA project WildBotics closes on Jan 7th. Hurry up. Topic DC-6: AI-based soundscape analysis wildbotics.eu/network/topics Details: wildbotics.eu/recruitment