🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

📢 The evaluation period of the Instruction Following task at IWSLT 2025 just started! 🖥️ Consider submitting your speech-to-text system! The outputs can be easily uploaded on the SPEECHM platform developed in the Meetween project! ➡️ iwslt2025.speechm.cloud.cyfronet.pl

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 🥳

Our pick of the week by Zhihang Xie: "Bridging Speech and Text Foundation Models with ReShape Attention" by かのう𝕏たかとも, William Chen, Shinji Watanabe, et al. (#ICASSP2025) ieeexplore.ieee.org/document/10888… #Speech #FoundationModel #SpeechProcessing

Our pick of the week by Marco Gaido: "OpenOmni: Advancing Open-Source Omnimodal Large Language Models with Progressive Multimodal Alignment and Real-Time Self-Aware Emotional Speech Synthesis" by Luo, Ting-En Lin, et al., 2025. #opensource #multimodal #alignment #speech #LLM

Happy to announce that our paper 'An LLM-as-a-judge Approach for Scalable Gender-Neutral Translation Evaluation' was accepted at #GITT2025! 🙌 Check it out: arxiv.org/abs/2504.11934 🔥 Co-authors (🫶🏻): BeatriceSavoldi, Matteo Negri, Luisa Bentivogli

Yesterday I celebrated #WorldVoiceDay at Università di Torino, sharing some thoughts and highlights from my research on AI and voice. A truly enjoyable event, with inspiring and diverse talks on the many dimensions of voice!

🎉 Excited to share that our Sara Papi has won the 2024 Best PhD Award from the Information and Engineering Doctoral School at UniTrento_DISI for her thesis “Direct Speech Translation in Constrained Contexts: The Simultaneous and Subtitling Scenarios.” #nlproc Fondazione Bruno Kessler - FBK

SHADES: a global dataset to uncover AI bias Over 50 researchers, 16 languages, thousands of interactions analysed: the international SHADES project investigates how generative language models (LLM) reproduce and amplify cultural stereotypes ◾magazine.fbk.eu/en/news/shades…

🎉 Excited to share our paper “Different Speech Translation Models Encode and Translate Speaker Gender Differently” was accepted at #ACL2025 (main)! ✍🏼 Big thanks to amazing co-authors: Marco Gaido, Matteo Negri, Luisa Bentivogli, Andre Martins, Giuseppe Attanasio! 📄 Preprint out soon!

More great news! 🎉 Our paper “Echoes of Phonetics: Unveiling Relevant Acoustic Cues for ASR via Feature Attribution” was accepted at #Interspeech2025! Interested in interpretability for speech models? Preprint coming soon! ✍🏼 Marco Gaido, Matteo Negri, M.Cettolo, Luisa Bentivogli

Our pick of the week by BeatriceSavoldi: "Lost in Translation: Artificial Intelligence and the Demand for Foreign Language Skills" by Pedro Llanos-Paredes ☀️ and Carl Benedikt Frey (2025) oxfordmartin.ox.ac.uk/publications/l… #AI #translation #MT

Pick of the week MT Group at FBK: arxiv.org/abs/2505.19606 by Ryan Soh-Eun Shim Domenico De Cristofaro. XAI work on cross-lingual alignment in speech-to-text models that disentangles phonetics and semantics. Plus: their XAI insights yield actionable improvements for low-resource language performance.

🚀 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

🔍 Ciao! Stiamo studiando come l'AI viene usata in Italia e per farlo abbiamo costruito un sondaggio! 👉bocconi.eu.qualtrics.com/jfe/form/SV_2n… (è anonimo, dura ~10 m, se partecipi o lo diffondi ci aiuti un sacco🙏) Ci interessa anche raggiungere persone che non si occupano di AI!

Cosa chiedono davvero gli italiani all’intelligenza artificiale? FBK in collaborazione con RiTA lancia un’indagine aperta a tutte/i per capire usi reali, abitudini e bisogni. Bastano 10 minuti per partecipare, scopri di più: magazine.fbk.eu/it/news/italia…

Our pick of the week by Beomseok LEE: "ALAS: Measuring Latent Speech-Text Alignment For Spoken Language Understanding In Multimodal LLMs" by Pooneh Mousavi, yingzhi wang, Mirco Ravanelli, and Cem Subakan (2025) arxiv.org/abs/2505.19937 #SLU #speech #multimodal #LLM

🚀 Last call for the Model Compression for Machine Translation task at #WMT2025 (co-located with #EMNLP2025)! Test data out on June 19 ➡️ 2 weeks for evaluation! Can you shrink an LLM and keep translation quality high? 👉 www2.statmt.org/wmt25/model-co… #NLP #ML #LLM #ModelCompression

Findings from ieeexplore.ieee.org/document/10669… show that speech SSL models converge on similar embedding spaces, but via different routes. While overall representations align, individual neurons learn distinct localized concepts. Interesting read! MT Group at FBK

Our pick of the week by Dennis Fucci: "Speech Representation Analysis Based on Inter- and Intra-Model Similarities" by Yassine El Kheir, Ahmed Ali, and Shammur Absar Chowdhury (ICASSP Workshops 2024) #speech #speechtech

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…