MT Group at FBK
@fbk_mt
Followers
1K
Following
3K
Media
389
Statuses
3K
#MachineTranslation Research Unit @FBK_research. #nlproc #deeplearning #ai
Trento, Trentino-South Tyrol
Joined October 2015
Our pick of the week by @lina_conti: "I Have No Mouth, and I Must Rhyme: Uncovering Internal Phonetic Representations in LLaMA 3.2" Oliver McLaughlin, Arjun Khurana, @jack_merullo_ (2025). #XAI #LLM #interpretability.
arxiv.org
Large language models demonstrate proficiency on phonetic tasks, such as rhyming, without explicit phonetic or auditory grounding. In this work, we investigate how \verb|Llama-3.2-1B-Instruct|...
Pick of the week @fbk_mt : "I Have No Mouth, and I Must Rhyme" đź‘„ a dive into how LLaMA develops internal phonetic representations despite never hearing speech. #XAI #LLM #interpretability.
0
0
2
RT @slatornews: 👉 At IWSLT 2025, researchers and industry share ways to boost ⚡ speed, 🌟 quality, 🎬 subtitles, mode….
slator.com
IWSLT 2025 brought ideas to speed up speech translation, improve quality, handle subtitles, and cover more languages.
0
2
0
RT @iwslt: 📢📢 We invite proposals for @iwslt 2026 shared tasks! For further information on this initiative, please refer to the https://t….
0
5
0
@sarapapi @DennisFucci @iwslt Finally, we contributed to "NUTSHELL: A Dataset for Abstract Generation from Scientific Talks" presented by @MaikeZufle from @Ai4Lt . 👉 (6/6).
0
0
5
1
0
6
@sarapapi @DennisFucci We organized 5 tasks at #IWSLT:.📌 Offline .📌 Simultaneous .📌 Subtitling .📌Model compression .📌 Instruction following. 👉 (4/6)
1
0
3
@sarapapi @DennisFucci shared insightful findings on gender bias through the lens of interpretability: "Different speech translation models encode and translate speaker gender differently". 👉(3/6)
1
0
4
Heading home after an exciting and intense @aclmeeting in Vienna! We had a great time presenting our work and connecting with the community. Thanks to everyone who came by! . #acl2025 #nlproc .(1/6)
5
2
25
RT @MaikeZufle: 🇦🇹 I’ll be in Vienna for #ACL2025NLP!. Interested in training a SpeechLLM without a lot of params or data? Come to my poste….
0
5
0
RT @ArxivSound: Sara Papi, Maike Z\"ufle, Marco Gaido, Beatrice Savoldi, Danni Liu, Ioannis Douros, Luisa Bentivogli, Jan Niehues, "MCIF: M….
arxiv.org
Recent advances in large language models have catalyzed the development of multimodal LLMs (MLLMs) that integrate text, speech, and vision within unified frameworks. As MLLMs evolve from narrow,...
0
3
0
Our pick of the week by @mgaido91: "WhisperKit: On-device Real-time ASR with Billion-Scale Transformers" by Atila Orhon, Arda Okan, Berkin Durmus, @zachnagengast, and Eduardo Pacheco (ICML 2025). . #speech #speechtech #whisper #ASR #realtime.
arxiv.org
Real-time Automatic Speech Recognition (ASR) is a fundamental building block for many commercial applications of ML, including live captioning, dictation, meeting transcriptions, and medical...
A couple of weeks before presenting our large-scale speech model compression task at IWSLT, here there is of the first attempts to bring large-scale models to the devices on the edge: Hope to see more works along this direction!.
0
0
3
Our pick of the week by @FBKZhihangXie: "Adversarial Speech-Text Pre-Training for Speech Translation" by Chenxuan Liu, Liping Chen, Weitai Zhang, Xiaoxi Li, Peiwang Tang, Mingjia Yu, Sreyan Ghosh, and Zhongyi Ye (ICASSP 2025). #speech #speechprocessing #speechtech #translation.
🚀 AdvST: Adversarial training aligns speech and text distributions without parallel data! Combines adversarial learning + hidden-state swapping to fix length mismatch & boost low-resource speech translation.
0
0
2
Thrilled to be part of this amazing project and team!.
🚀 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
0
0
3
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.
🚀 Boost rare-phrase translation in speech! Uses **bilingual dictionaries** to dynamically bias outputs. ✅ **+21%** recall in streaming ST .✅ **+85%** in multimodal LLMs .🔗:
0
0
2
RT @FBK_research: FAMA è il primo foundation model vocale open-science per ita e eng, sviluppato da FBK. Riconosce e traduce la voce usando….
0
11
0
Our pick of the week by @DennisFucci: "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.
Findings from 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! @fbk_mt.
0
2
3
RT @FBK_research: Cosa chiedono davvero gli italiani all’intelligenza artificiale?.FBK in collaborazione con RiTA lancia un’indagine aperta….
0
6
0