@sarapapi.bsky.social
๐ค 106
๐ฅ 102
๐ 16
(she/her) Postdoc at
@fbk-mt.bsky.social
| Working on speech translation
reposted by
MT Group at FBK
21 days ago
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
0
2
1
reposted by
AILC-NLP
about 2 months ago
Thanks to all the participants!
#clicit2025
0
11
5
reposted by
MT Group at FBK
about 2 months ago
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
0
5
2
reposted by
AILC-NLP
about 2 months ago
Last oral session of the first
#clicit2025
day! See you all at the welcome drink!
0
2
1
Iโm the guest ๐๐ปโโ๏ธ
add a skeleton here at some point
about 2 months ago
0
2
0
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
about 2 months ago
0
7
2
An interesting survey about
#RAG
and its interplay with
#multimodality
: Retrieval-Augmented Generation for AI-Generated Content: A Survey
arxiv.org/pdf/2402.19473
@fbk-mt.bsky.social
loading . . .
https://arxiv.org/pdf/2402.19473
2 months ago
0
0
1
reposted by
AI Research Updates | arXiv cs.AI
4 months ago
MCIF: Multimodal Crosslingual Instruction-Following Benchmark from Scientific Talks Read more:
https://arxiv.org/html/2507.19634v1
0
1
1
reposted by
arxiv cs.CL
4 months ago
Sara Papi, Maike Z\"ufle, Marco Gaido, Beatrice Savoldi, Danni Liu, Ioannis Douros, Luisa Bentivogli, Jan Niehues MCIF: Multimodal Crosslingual Instruction-Following Benchmark from Scientific Talks
https://arxiv.org/abs/2507.19634
0
4
4
reposted by
MT Group at FBK
4 months ago
@sarapapi.bsky.social
presented her TACL paper: โHow real is your real-time simultaneous speech-to-text translation system?โ ๐
aclanthology.org/2025.tacl-1.14/
(2/6)
1
3
1
๐ฅ Is your real-time SimulST system REAL? Our TACL paper analyzes 110 works and reveals: ๐ซ Overreliance on short-form speech ๐ Terminology chaos ๐ Real-world deployment gaps We bring order-New taxonomy, trends & recommendations! ๐#ACL2025 Poster: Monday 11-12:30, Hall 4/5
#Speech
#SpeechTech
4 months ago
1
5
0
reposted by
Beatrice Savoldi
6 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
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
6 months ago
0
7
3
reposted by
Tiago Pimentel
6 months ago
If you're finishing your camera-ready for ACL or ICML and want to cite co-first authors more fairly, I just made a simple fix to do this! Just add $^*$ to the authors' names in your bibtex, and the citations should change :)
github.com/tpimentelms/...
4
85
23
I am honored to have received this award today! ๐
add a skeleton here at some point
6 months ago
0
4
0
reposted by
IWSLT
8 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
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
8 months ago
0
9
5
I'm thrilled to be one of the speakers at the next MT Marathon in Helsinki ๐ I look forward to sharing insights on automatic translation and related topics with our community!
add a skeleton here at some point
8 months ago
0
2
0
Glad to see that the model weights of the new Step-Audio, a speech foundation model + large language model (+ speech decoder) architecture, are published under open licenses! ๐
arxiv.org/abs/2502.11946
loading . . .
Step-Audio: Unified Understanding and Generation in Intelligent Speech Interaction
Real-time speech interaction, serving as a fundamental interface for human-machine collaboration, holds immense potential. However, current open-source models face limitations such as high costs in vo...
https://arxiv.org/abs/2502.11946
9 months ago
0
4
1
reposted by
GITT 2025
9 months ago
As if you needed more reasons to submit to
#GITT2025
: ๐๐ต Cristina Anselmi, video game
#localization
&
#AI
expert with a focus on
#inclusive
#language
will be our keynote speaker! ๐ธRegistration fees are on the MTSummit website and you can register just for GITT if you so choose ๐ ๐ See you there! ๐
0
13
10
I'm happy to share that our paper "Prepending or Cross-Attention for Speech-to-Text? An Empirical Comparison" has been accepted at
@naaclmeeting.bsky.social
2025!
#NAACL2025
@mgaido91.bsky.social
๐ ๐ Preprint:
arxiv.org/abs/2501.02370
โฐ Code will be released soon
#NLProc
#Speech
loading . . .
Prepending or Cross-Attention for Speech-to-Text? An Empirical Comparison
Following the remarkable success of Large Language Models (LLMs) in NLP tasks, there is increasing interest in extending their capabilities to speech -- the most common form in communication. To integ...
https://arxiv.org/abs/2501.02370
10 months ago
0
10
3
reposted by
GITT 2025
10 months ago
Hello world! ๐ We're coming out of hibernation to bring you this happy news: 1) We're organising the 3rd edition of GITT at
#MTSummit
! Working on
#gender
&
#translation
#technology
? We'll see you there! 2) We're moving away from Twitter, so share the news and help us find old and new GITT friends!
0
27
16
reposted by
MT Group at FBK
10 months ago
๐ All members of our group are now on Bluesky! ๐ You can find all of us in this starter pack ๐
add a skeleton here at some point
0
6
5
Exciting news: IWSLT will be co-located with
@aclmeeting.bsky.social
2025 again this year! ๐ Interested in speech processing? Check out the new task on instruction following โ any model can participate! ๐ ๐ Data release: April 1 โณ Submission deadline: April 15 ๐ฌ
iwslt.org/2025/instruc...
loading . . .
Instruction-following Speech Processing track
Home of the IWSLT conference and SIGSLT.
https://iwslt.org/2025/instruction-following
10 months ago
0
11
5
Iโm glad to announce that our work โHow "Real" is Your Real-Time Simultaneous Speech-to-Text Translation System?โ has been accepted at the Transactions of
@aclmeeting.bsky.social
(TACL)! ๐ The preprint is available here:
arxiv.org/pdf/2412.18495
loading . . .
https://arxiv.org/pdf/2412.18495
11 months ago
0
7
2
reposted by
MT Group at FBK
12 months ago
Our
@apierg.bsky.social
presenting our
#calamita
challenges at
#CLiCit2024
: machine translation and gender-fair generation. Poster session upcoming, see you there! For more details: ๐ MagneT:
clic2024.ilc.cnr.it/wp-content/u...
๐ GFG:
clic2024.ilc.cnr.it/wp-content/u...
0
9
2
๐ Interested in Simultaneous Translation? We're organizing the IWSLT SimulST Shared Task and would love your input for the 2025 edition. ๐ฃ๏ธ ๐ Share your thoughts here:
forms.gle/LwkF3284NzZd...
loading . . .
IWSLT 2025 SimulST Shared Task Survey
A survey taking about 3-5 minutes that will assist organizers in shaping how the aforementioned shared task is structured at IWSLT 2025.
https://forms.gle/LwkF3284NzZdQPc38
12 months ago
0
4
1
reposted by
MT Group at FBK
12 months ago
Today
@luisabentivogli.bsky.social
, Dennis Fucci, and
@apierg.bsky.social
presented a research communication about gender-neutral translation in the morning poster session
#CLiCit2024
#NLProc
1
20
4
reposted by
MT Group at FBK
12 months ago
We are happy to announce that our PhD students Dennis Fucci and
@apierg.bsky.social
along with our head of unit
@luisabentivogli.bsky.social
, will attend
#CLiCit2024
in Pisa! Meet them at the poster presentations during the main conference and the
#CALAMITA
event!
loading . . .
Dennis Fucci, Andrea Piergentili, and Luisa Bentivogli at CLiC-it 2024 | Machine Translation Unit
https://mt.fbk.eu/dennis-fucci-andrea-piergentili-and-luisa-bentivogli-at-clic-it-2024/
0
8
4
reposted by
Debora Nozza
12 months ago
Iโve created an Italian
#NLProc
Researcher Starter Pack ๐ฎ๐น DM me to join if you're not in yet!
go.bsky.app/LHbWLHp
add a skeleton here at some point
0
24
5
reposted by
MT Group at FBK
12 months ago
With our first post on Bluesky we are glad to announce that our
@sarapapi.bsky.social
received the Special Mention for the Best PhD Thesis Award assigned by AIxIA 2024!
mt.fbk.eu/our-postdoc-...
0
8
1
you reached the end!!
feeds!
log in