• Future Built on Knowledge
Machine Translation Unit
  • Home
  • People
  • Research
  • Projects
  • Publications
  • Resources
  • Join us
  • LOGIN

Select Page

Findings of the IWSLT 2022 Evaluation Campaign.

MT Group at FBK Follow

#MachineTranslation Research Unit @FBK_research. #nlproc #deeplearning #ai

Avatar
Retweet on Twitter MT Group at FBK Retweeted
Avatar DVPS @dvps_ai ·
4 Jul

A special evening in Rome to talk about Physical AI and Europe’s role in shaping this new frontier.

Partners from across Europe came together to present the DVPS project, and connect with key people from public institutions, embassies, industries, national & international media.

Reply on Twitter 1941079592242151811 Retweet on Twitter 1941079592242151811 4 Like on Twitter 1941079592242151811 7 Twitter 1941079592242151811
Avatar MT Group at FBK @fbk_mt ·
16h

Thrilled to be part of this amazing project and team!

DVPS @dvps_ai

πŸš€ DVPS has launched at Translated's HQ!
70 researchers from 20 institutions across 9 countries unite to build next-gen multimodal foundation models that learn from real-world interaction.
A new European AI journey begins.
#DVPS #PhysicalAI #HorizonEurope #MultimodalAI

Reply on Twitter 1941818149499723814 Retweet on Twitter 1941818149499723814 Like on Twitter 1941818149499723814 2 Twitter 1941818149499723814
Avatar MT Group at FBK @fbk_mt ·
3 Jul

Our pick of the week by @FBKZhihangXie: "PHRASED: Phrase Dictionary Biasing for Speech Translation" by Peidong Wang, Jian Xue, Rui Zhao, @ChenJunkun, Aswin Shanmugam Subramanian, and Jinyu Li (2025).

#Speech #SpeechAI #Translation #ST #SpeechTranslation

Zhihang Xie @FBKZhihangXie

πŸš€ Boost rare-phrase translation in speech! Uses **bilingual dictionaries** to dynamically bias outputs.
βœ… **+21%** recall in streaming ST
βœ… **+85%** in multimodal LLMs
πŸ”—: http://arxiv.org/abs/2506.09175

Reply on Twitter 1940680349392294302 Retweet on Twitter 1940680349392294302 Like on Twitter 1940680349392294302 2 Twitter 1940680349392294302
Retweet on Twitter MT Group at FBK Retweeted
Avatar Fondazione Bruno Kessler - FBK @fbk_research ·
30 Jun

FAMA Γ¨ 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 @fbk_mt

https://magazine.fbk.eu/it/news/la-prima-famiglia-di-modelli-open-science-per-il-riconoscimento-vocale-e-la-traduzione-del-parlato/

Reply on Twitter 1939609858812027189 Retweet on Twitter 1939609858812027189 10 Like on Twitter 1939609858812027189 14 Twitter 1939609858812027189
Load More

Contact: dicenter-webmaster@fbk.eu
The use of content covered by intellectual property is carried out in compliance with articles 2, 21, 33 of the Constitution and art. 70 of the copyright law.
This publication was produced with the support of the Autonomous Province of Trento.