MT Group at FBK
@fbk-mt.bsky.social
๐ค 191
๐ฅ 175
๐ 60
#MachineTranslation
Research Unit @ Fondazione Bruno Kessler
#nlproc
#deeplearning
#ai
mt.fbk.eu
Our pick of the week by
@zhihangxie.bsky.social
: "#Speech Discrete Tokens or Continuous Features? A Comparative Analysis for Spoken Language Understanding in
#SpeechLLMs
" by Dingdong Wang, Junan Li, Mingyu Cui, et al. (#EMNLP2025)
aclanthology.org/2025.emnlp-m...
#SLU
#SpeechTech
add a skeleton here at some point
1 day ago
0
2
0
๐ Exciting news from the
@fbk-mt.bsky.social
group!
@bsavoldi.bsky.social
,
@linaconti.bsky.social
,
@matteo-negri.bsky.social
&
@luisabentivogli.bsky.social
are attending
#EMNLP2025
in Suzhou ๐จ๐ณ! Come to our sessions & let's connect: ๐
mt.fbk.eu/fbk-mt-at-em...
Weโre also hiring postdocs!โก
10 days ago
0
5
2
๐๐Congratulations to our PhD student
@dennisfucci.bsky.social
on a very successful thesis defense! ๐ Many thanks to the evaluation committee members
@deboranozza.bsky.social
, Mirco Ravanelli, and Leonardo Badino for their insightful feedback and appreciation of his work!
#nlproc
13 days ago
0
2
0
reposted by
MT Group at FBK
DH Group at FBK
14 days ago
@bsavoldi.bsky.social
from
@fbk-mt.bsky.social
will present Translation in the Hands of Many: Centering Lay Users in Machine Translation Interactions at the poster session on Wed Nov. 5th, 11:00-12:30 in Hall C
0
5
2
Our
#PickOfTheWeek
by
@beomseok-lee.bsky.social
: "Can Speech LLMs Think while Listening?" by Yi-Jen Shih,
@rdesh26.bsky.social
, Chunyang Wu, Wei Zhou, SK Bong, Yashesh Gaur, Jay Mahadeokar, Ozlem Kalinli, Mike Seltzer (2025).
#Speech
#SpeechLLM
#LLM
#SpeechTech
#AI
add a skeleton here at some point
16 days ago
0
0
0
Our next presentation is by
@sarapapi.bsky.social
: "How real is your real-time simultaneous speech-to-text translation system?" Look for the answer in her TACL paper:
direct.mit.edu/tacl/article...
#lt2025fbk
17 days ago
0
2
1
Our Marco Gaido presenting FAMA, the first family of large-scale open-science speech foundation models for English and Italian. Joint work with the
@speechtekfbk.bsky.social
group. Data, code, models publicly available, check all info in the paper:
clic2025.unica.it/wp-content/u...
#lt2025fbk
17 days ago
0
1
0
@bsavoldi.bsky.social
presenting our new multilingual benchmark for evaluating LLMs on gender-neutral translation. Catch our paper at
#EMNLP2025
โน๏ธ
arxiv.org/pdf/2501.09409
#lt2025fbk
17 days ago
0
4
1
Now it's the turn of our
@dennisfucci.bsky.social
presenting the
#ACL2025NLP
paper on explaining gender bias in speech translation ๐
aclanthology.org/2025.acl-sho...
#lt2025fbk
17 days ago
0
2
0
The Language Technology at FBK workshop has just started with a truly insightful talk by
@deboranozza.bsky.social
: "A Roadmap for the Everyday Use of LLMs: Emerging Risks and Research Directions"
#LT2025FBK
17 days ago
1
2
0
Our pick of the week by
@linaconti.bsky.social
: "Lost in Transcription, Found in Distribution Shift: Demystifying Hallucination in Speech Foundation Models" by Hanin Atwany,
@abdulwaheed.bsky.social
, Rita Singh, Monojit Choudhury, and Bhiksha Raj (ACL Findings 2025)
aclanthology.org/2025.finding...
add a skeleton here at some point
22 days ago
0
1
0
๐ Join us for the LT@FBK day 2025! Discover cutting-edge research and highlights in speech and language technologies from Fondazione Bruno Kessler (FBK) ๐ October 28, 2025 ๐FBK, Trento โน๏ธ
lt-highlights.fbk.eu
loading . . .
LT Highlights @ FBK 2025
https://lt-highlights.fbk.eu
24 days ago
0
3
1
Our pick of the week by
@bsavoldi.bsky.social
: "Acoustic-based Gender Differentiation in Speech-aware Language Models" by Junhyuk Choi, Jihwan Seol, Nayeon Kim, Chanhee Cho, EunBin Cho, Bugeun Kim.
arxiv.org/abs/2509.21125
#Gender
#SpeechLLM
#Speech
add a skeleton here at some point
29 days ago
0
0
0
reposted by
MT Group at FBK
29 days ago
๐ Our annual, full-day Language Technologies showcase is back! Dive into the latest research highlights fromย FBK groups. Want in? We'd love to see you, but don't forget to register!
www.fbk.eu/en/event/346...
loading . . .
Language Technology Research Highlights 2025
The Language Technology Research Highlights 2025 (LT@FBK2025) event aims to bring together scientists, students, practitioners, and enthusiasts who are interested in language technologies and want to ...
https://www.fbk.eu/en/event/34674/language-technology-research-highlights-2025/
0
2
3
Marco Gaido introducing SimulStream, an
#OpenSource
Tool for Simultaneous
#Speech
#Translation
๐ฃ๏ธ๐ฅ๏ธ๐ at the DI Center Demo Day at FBK! The tool is going to be released soon. Stay tuned! ๐
about 1 month ago
0
1
0
Marco Gaido and Roldano Cattoni presenting our SimulStream Demo at the DI Center Demo Day at FBK! The open-source tool, which is going to be released soon, natively supports any speech-to-text
#HuggingFace
models! ๐ค
#SpeechTech
#Translation
about 1 month ago
0
1
0
reposted by
MT Group at FBK
Lina Conti
about 1 month ago
๐ Excited to share that my paper "The Unheard Alternative" was accepted to
@blackboxnlp.bsky.social
2025! We introduce contrastive explanations for speech-to-text, identifying which audio features ST models use to assign a grammatical gender to the speaker. ๐ Preprint:
arxiv.org/abs/2509.265...
loading . . .
The Unheard Alternative: Contrastive Explanations for Speech-to-Text Models
Contrastive explanations, which indicate why an AI system produced one output (the target) instead of another (the foil), are widely regarded in explainable AI as more informative and interpretable th...
https://arxiv.org/abs/2509.26543v1
0
2
1
Our very own
@sarapapi.bsky.social
presenting FAMA at
#clicit2025
: ๐Paper:
clic2025.unica.it/wp-content/u...
๐ Models:
hf.co/collections/...
๐ Data:
hf.co/datasets/FBK...
๐ป Code:
github.com/hlt-mt/FBK-f...
Joint work with
@speechtekfbk.bsky.social
about 2 months ago
0
5
2
reposted by
MT Group at FBK
about 2 months ago
๐ Excited to present FAMA, the first large-scale
#OpenScience
#Speech
foundation model for ๐ฎ๐น Italian & ๐ฌ๐ง English, at
#clicit2025
(17:30โ18:45 oral session)! ๐ Models:
hf.co/collections/...
๐ Data:
hf.co/datasets/FBK...
๐ป Code:
github.com/hlt-mt/FBK-f...
๐ Preprint:
arxiv.org/pdf/2505.22759
0
7
2
reposted by
MT Group at FBK
DH Group at FBK
about 2 months ago
We are on our way to Casteddu for
#clicit2025
with a guest from
@fbk-mt.bsky.social
@ailc-nlp.bsky.social
0
7
6
Our pick of the week by
@sarapapi.bsky.social
: "Retrieval-Augmented Generation for AI-Generated Content: A Survey" by Penghao Zhao, Hailin Zhang, Qinhan Yu, Zhengren Wang, Yunteng Geng, Fangcheng Fu, Ling Yang, Wentao Zhang, Jie Jiang, Bin Cui.
arxiv.org/pdf/2402.19473
#RAG
#survey
add a skeleton here at some point
about 2 months ago
0
0
0
Our pick of the week by Marco Gaido: "Context-Driven Dynamic
#Pruning
for Large
#Speech
#Foundation
Models" by Masao Someki, Shikhar Bharadwaj, Atharva Anand Joshi, Chyi-Jiunn Lin, Jinchuan Tian, Jee-weon Jung,
@shinjiw.bsky.social
, et al.
#INTERSPEECH2025
.
arxiv.org/abs/2505.18860
loading . . .
Context-Driven Dynamic Pruning for Large Speech Foundation Models
Speech foundation models achieve strong generalization across languages and acoustic conditions, but require significant computational resources for inference. In the context of speech foundation mode...
https://arxiv.org/abs/2505.18860
2 months ago
0
2
0
Our pick of the week by
@zhihangxie.bsky.social
: "SimulMEGA: MoE Routers are Advanced Policy Makers for Simultaneous Speech Translation" by Chenyang Le, Bing Han, Jinshun Li, Songyong Chen, and Yanmin Qian (2025)
#Speech
#Simultaneous
#Translation
#MOE
#SpeechTech
add a skeleton here at some point
2 months ago
0
0
0
Our pick of the week by
@beomseok-lee.bsky.social
: "Speech Discrete Tokens or Continuous Features? A Comparative Analysis for Spoken Language Understanding in SpeechLLMs" by Dingdong Wang, Junan Li, Mingyu Cui, Dongchao Yang, Xueyuan Chen, and Helen Meng (EMNLP 2025)
add a skeleton here at some point
3 months ago
0
2
0
Our pick of the week by
@linaconti.bsky.social
: "I Have No Mouth, and I Must Rhyme: Uncovering Internal Phonetic Representations in LLaMA 3.2"
@jackmerullo.bsky.social
, Arjun Khurana, Oliver McLaughlin (ICML 2025 Workshop on Assessing World Models)
arxiv.org/abs/2508.02527
#XAI
#LLM
add a skeleton here at some point
3 months ago
0
0
0
Heading home after an exciting and intense
@aclmeeting.bsky.social
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)
3 months ago
1
5
1
Before presenting our speech model compression task at IWSLT, our pick of the week by Marco Gaido: WhisperKit
arxiv.org/abs/2507.10860
by Atila Orhon, Arda Okan, Berkin Durmus, Zach Nagengast and
@eduardo-pacheco.bsky.social
(ICML 2025)โan early attempt to bring large-scale models to edge devices
loading . . .
WhisperKit: On-device Real-time ASR with Billion-Scale Transformers
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 scribes. ...
https://arxiv.org/abs/2507.10860
4 months ago
0
2
0
Our pick of the week by
@zhihangxie.bsky.social
: "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)
add a skeleton here at some point
4 months ago
0
0
0
Our pick of the week by
@zhihangxie.bsky.social
๐: "PHRASED: Phrase Dictionary Biasing for Speech Translation" by Peidong Wang, Jian Xue, Rui Zhao, Junkun Chen, Aswin Shanmugam Subramanian, Jinyu Li
arxiv.org/abs/2506.09175
#speech
#AI
#ST
#NLP
add a skeleton here at some point
4 months ago
0
2
0
reposted by
MT Group at FBK
GITT 2025
5 months ago
@bsavoldi.bsky.social
taking us back in time at
#GITT2025
โโณ focusing on the first discussions of gender bias in language technology as a socio-technical issue. No, the problem hasn't been fixed yet. But what has happened?
6
7
3
reposted by
MT Group at FBK
GITT 2025
5 months ago
Last but definitely not least:
@bsavoldi.bsky.social
presenting joint work with
@apierg.bsky.social
@matteo-negri.bsky.social
@luisabentivogli.bsky.social
on scalable gender neutral translation evaluation using LLM-as-a-judge at
#GITT2025
6
10
4
Our pick of the week by
@dennisfucci.bsky.social
: "Speech Representation Analysis Based on Inter- and Intra-Model Similarities" by
@yelkheir.bsky.social
,
@ratedali.bsky.social
, and Shammur Absar Chowdhury (ICASSP Workshops 2024)
add a skeleton here at some point
5 months ago
0
4
1
Our pick of the week by
@beomseok-lee.bsky.social
: "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
add a skeleton here at some point
5 months ago
0
2
0
Our pick of the week by
@apierg.bsky.social
: "Agree to Disagree? A Meta-Evaluation of LLM Misgendering" by Arjun Subramonian,
@dippedrusk.com
, Preethi Seshadri, Dietrich Klakow, Kai-Wei Chang, and Yizhou Sun
#LLM
#NLProc
#fairness
add a skeleton here at some point
5 months ago
0
3
0
reposted by
MT Group at FBK
Beatrice Savoldi
5 months ago
๐ Stiamo studiando come l'AI viene usata in Italia e per farlo abbiamo costruito un sondaggio! ๐
bit.ly/sondaggio_ai...
(รจ anonimo, richiede ~10 minuti, e se partecipi o lo fai girare ci aiuti un sacco๐) Ci interessa anche raggiungere persone che non si occupano e non sono esperte di AI!
loading . . .
Qualtrics Survey | Qualtrics Experience Management
The most powerful, simple and trusted way to gather experience data. Start your journey to experience management and try a free account today.
https://bit.ly/sondaggio_ai_rita
1
16
18
reposted by
MT Group at FBK
6 months ago
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 @hf.co: ๐
huggingface.co/collections/...
๐ Preprint:
arxiv.org/abs/2505.22759
#ASR
#ST
#OpenScience
#MultilingualAI
loading . . .
FAMA - a FBK-MT Collection
The First Large-Scale Open-Science Speech Foundation Model for English and Italian
https://huggingface.co/collections/FBK-MT/fama-683425df3fb2b3171e0cdc9e
0
7
3
Our pick of the week by
@linaconti.bsky.social
: "Languages in Multilingual Speech Foundation Models Align Both Phonetically and Semantically", by โช@soheunshim.bsky.social, Domenico De Cristofaro, Chengzhi Martin Hu, โช@alessandrovietti.bsky.social,
@barbaraplank.bsky.social
#AI
#XAI
#speech
#nlproc
add a skeleton here at some point
6 months ago
0
4
0
Our pick of the week by
@bsavoldi.bsky.social
: "Lost in Translation: Artificial Intelligence and the Demand for Foreign Language Skills" by
@pmllanos.bsky.social
and
@carlbfrey.bsky.social
(2025)
oxfordmartin.ox.ac.uk/publications...
#AI
#translation
#MT
add a skeleton here at some point
6 months ago
0
3
0
reposted by
MT Group at FBK
Dennis Fucci
6 months ago
So happy our paper โDifferent Speech Translation Models Encode and Translate Speaker Gender Differentlyโ was accepted at
#ACL2025
(main)! ๐ The preprint will be out soon!
#SpeechTranslation
#GenderBias
#Interpretability
@aclmeeting.bsky.social
1
7
1
๐ Excited to share that our
@sarapapi.bsky.social
has won the 2024 Best PhD Award from the Information and Engineering Doctoral School for her thesis โDirect Speech Translation in Constrained Contexts: The Simultaneous and Subtitling Scenarios.โ
#nlproc
#speech
#speechprocessing
#speechtranslation
6 months ago
0
6
2
๐ข One week left to apply for a fully funded 3-year PhD position in our group! ๐Automatic translation with large multimodal models:
iecs.unitn.it/education/ad...
๐Full details for application:
iecs.unitn.it/education/ad...
๐ Deadline: 12 May 2025, 4pm CEST
#NLProc
#FBK
6 months ago
0
4
4
reposted by
MT Group at FBK
GITT 2025
7 months ago
๐ญDreaming of attending
#GITT2025
but need a little extra ๐ธ boost? ๐ฃ Bursary applications to support participation are now open at
tinyurl.com/gitt25
๐ Deadline May 9th ๐Thanks to our incredible sponsors DCA at Tilburg University
tinyurl.com/tudca25
and FLW at Ghent University
www.ugent.be/lw/en
1
7
7
๐ข Come and join our group! We offer a fully funded 3-year PhD position: ๐ Automatic translation with large multimodal models:
iecs.unitn.it/education/ad...
๐Full details for application:
iecs.unitn.it/education/ad...
๐ Deadline May 12, 2025
#NLProc
#FBK
loading . . .
Reserved topic scholarships | Doctoral Program - Information Engineering and Computer Science
https://iecs.unitn.it/education/admission/reserved-topic-scholarships#A4
7 months ago
1
10
10
reposted by
MT Group at FBK
Andrea Piergentili
7 months ago
Happy to announce that our paper 'An LLM-as-a-judge Approach for Scalable Gender-Neutral Translation Evaluation' was accepted at
@gitt-workshop.bsky.social
! ๐ Check it out:
arxiv.org/abs/2504.11934
๐ฅ Co-authors (๐ซถ๐ป):
@bsavoldi.bsky.social
,
@matteo-negri.bsky.social
,
@luisabentivogli.bsky.social
loading . . .
An LLM-as-a-judge Approach for Scalable Gender-Neutral Translation Evaluation
Gender-neutral translation (GNT) aims to avoid expressing the gender of human referents when the source text lacks explicit cues about the gender of those referents. Evaluating GNT automatically is pa...
https://arxiv.org/abs/2504.11934
0
10
3
Our pick of the week by
@mgaido91.bsky.social
: "OpenOmni: Advancing Open-Source Omnimodal Large Language Models with Progressive Multimodal Alignment and Real-Time Self-Aware Emotional Speech Synthesis" by Luo et al. (2025)
#SpeechProcessing
#LLM
#SFM
#NLProc
#speechtech
#audio
add a skeleton here at some point
7 months ago
0
3
0
reposted by
MT Group at FBK
IWSLT
7 months ago
๐๏ธ Deadline update ๐๏ธ To accommodate requests, we have extended the test period for *all tasks* until *April 19th.* System description papers are now due *April 24th.* Thank you and good luck to all participants!!
0
2
1
Our pick of the week by
@zhihangxie.bsky.social
: "Bridging Speech and Text Foundation Models with ReShape Attention" by Takatomo Kano,
@wanchichen.bsky.social
,
@shinjiw.bsky.social
, et al.
#ICASSP2025
ieeexplore.ieee.org/document/108...
#FoundationModel
#SpeechProcessing
add a skeleton here at some point
7 months ago
0
3
0
reposted by
MT Group at FBK
IWSLT
7 months ago
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! โฐ Please email task organizers or the google group with any questions ๐ฅณ
0
6
4
Our pick of the week by
@beomseok-lee.bsky.social
: "AlignFormer: Modality Matching Can Achieve Better Zero-shot Instruction-Following Speech-LLM" by Ruchao Fan, Bo Ren, Yuxuan Hu, Rui Zhao, Shujie Liu, and Jinyu Li (2024).
#speech
#LLM
#speechlmm
#zeroshot
#instructionfollowing
add a skeleton here at some point
7 months ago
0
1
0
reposted by
MT Group at FBK
8 months ago
๐ข The evaluation period of the Instruction Following task at
@iwslt.bsky.social
just started! ๐ฅ๏ธ Consider submitting your speech-to-text system! The outputs can be easily uploaded on the SPEECHM platform developed in the Meetween project (
www.meetween.eu
)! โก๏ธ
iwslt2025.speechm.cloud.cyfronet.pl
loading . . .
https://iwslt2025.speechm.cloud.cyfronet.pl
0
9
5
Load more
feeds!
log in