The Machine Translation group at Fondazione Bruno Kessler specializes in speech and text technologies for multilingual communication. We work on innovative neural architectures and multimodal resources for a range of topics and applications (e.g. subtitling, interpreting, gender inclusivity). We are part of the Digital Industry center.
If you are fascinated by languages, cutting edge technology and research challenges, check out our Join Us page!
3 Papers Accepted at INTERSPEECH 2026
Jun 11, 2026
We’re glad to share that the three papers, co-authored by our Machine Translation Group at FBK,...
-
MT Unit at LREC 2026 🏝️
May 11, 2026
-
Celebrating Beomseok LEE’s PhD Defense 🎓
Apr 24, 2026
-
Sara Papi at ICLR 𝟮𝟬𝟮𝟲 🇧🇷
Apr 22, 2026
-
Celebrating Andrea Piergentili’s PhD Defense 🎓
Apr 20, 2026
-
Our pick of the week by
@lina_conti
: "Greater accessibility can amplify discrimination in generative AI" by
@CarolinHolterm, @minhducbui_nlp, @KaitlynZhou, @vjhofmann, @kelina1124, @anne_lauscher
📰
#GenderBias #SpeechLLM
Pick of the week @fbk_mt: "Greater accessibility can amplify discrimination in generative AI"
Gender bias in speech-based LLMs examined from multiple angles: a user survey, automatic bias measurement, and pitch manipulation experiments.
https://arxiv.org/pdf/2603.22260
Late update, but we had two great talks last month!
#MachineTranslation #FBK #NLProc #GenderBias #SpeechSynthesis
Our pick of the week by @dhairya_su47605
: "Scaling Laws for Precision" by @tanishqkumar07, Zachary Ankner, @bfspectorShiekh, @blake__bordelon, @Muennighoff, @mansiege, @CPehlevan, Christopher R´e, @AdtRaghunathan
📰
#Quantization #LLM #ScalingLaw
Pick of the week @fbk_mt
Super interesting paper on the limitations of quantization, demonstrating how post-training quantization scales poorly in data.
https://arxiv.org/abs/2411.04330
⭐ For our #PickOfTheWeek, this paper explores an important question for modern speech AI:
🎙️ Which Evaluation for Which Speech Model?
👥 Authors: @Maureendss , @EeshanDhekane
Speech foundation models are evolving rapidly, but evaluation practices are still fragmented.