An investment by the Autonomous Province of Trento in young talents involved in projects in synergy between FBK and the University of Trento on common research and highly innovative technological development initiatives that will pave the way for market and societal impact. The research activities will take place in the 4 macro-areas of Integrative AI, AI at the edge, Certified AI, and Interactive AI.
๐ New tech report out! Meet FAMA, our open-science speech foundation model family for both ASR and ST in ๐ฌ๐ง English and ๐ฎ๐น Italian.
The models are live and ready to try on @huggingface ๐
๐
#ASR #ST #OpenScience #MultilingualAI
Our pick of the week by @lina_conti: "Languages in Multilingual Speech Foundation Models Align Both Phonetically and Semantically" by @soheunshim, Domenico De Cristofaro, Chengzhi Martin Hu, Alessandro Vietti, and @barbara_plank (2025).
#speech #SFM #multilingual #speechtech
Pick of the week @fbk_mt: https://arxiv.org/abs/2505.19606 by @soheunshim @DomenicoDeCris1. 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.
๐ New shared task at #WMT2025 (co-located with @emnlpmeeting ): Model Compression for Machine Translation!
Can you shrink an LLM and keep translation quality high?๐ง
Submit by July 3 and push the limits of efficient NLP!
๐ https://www2.statmt.org/wmt25/model-compression.html #NLP #ML #LLM #ModelCompression
More great news! ๐
Our paper โEchoes of Phonetics: Unveiling Relevant Acoustic Cues for ASR via Feature Attributionโ was accepted at #Interspeech2025!
Interested in interpretability for speech models? Preprint coming soon!
โ๐ผ @mgaido91, @negri_teo, M.Cettolo, @luisabentivogli