's Avatar

@sarapapi.bsky.social

(she/her) Postdoc at @fbk-mt.bsky.social | Working on speech translation

98 Followers  |  98 Following  |  13 Posts  |  Joined: 02.12.2024  |  1.6748

Latest posts by sarapapi.bsky.social on Bluesky

Post image

@sarapapi.bsky.social presented her TACL paper: โ€œHow real is your real-time simultaneous speech-to-text translation system?โ€

๐Ÿ‘‰ aclanthology.org/2025.tacl-1.14/
(2/6)

02.08.2025 16:31 โ€” ๐Ÿ‘ 3    ๐Ÿ” 1    ๐Ÿ’ฌ 1    ๐Ÿ“Œ 0
Preview
How โ€œRealโ€ is Your Real-Time Simultaneous Speech-to-Text Translation System?

Official paper: direct.mit.edu/tacl/article...

27.07.2025 13:23 โ€” ๐Ÿ‘ 1    ๐Ÿ” 0    ๐Ÿ’ฌ 0    ๐Ÿ“Œ 0
Post image

๐Ÿ”ฅ Is your real-time SimulST system REAL?

Our TACL paper analyzes 110 works and reveals:
๐Ÿšซ Overreliance on short-form speech
๐ŸŒ€ Terminology chaos
๐Ÿ“‰ Real-world deployment gaps
We bring order-New taxonomy, trends & recommendations!

๐Ÿ“#ACL2025 Poster: Monday 11-12:30, Hall 4/5

#Speech #SpeechTech

27.07.2025 13:17 โ€” ๐Ÿ‘ 5    ๐Ÿ” 0    ๐Ÿ’ฌ 1    ๐Ÿ“Œ 0
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.

๐Ÿ” Stiamo studiando come l'AI viene usata in Italia e per farlo abbiamo costruito un sondaggio!

๐Ÿ‘‰ bit.ly/sondaggio_ai...

(รจ anonimo, richiede ~10 minuti, e se partecipi o lo fai girare ci aiuti un sacco๐Ÿ™)

Ci interessa anche raggiungere persone che non si occupano e non sono esperte di AI!

03.06.2025 10:24 โ€” ๐Ÿ‘ 16    ๐Ÿ” 18    ๐Ÿ’ฌ 1    ๐Ÿ“Œ 0
Preview
FAMA - a FBK-MT Collection The First Large-Scale Open-Science Speech Foundation Model for English and Italian

๐Ÿš€ New tech report out! Meet FAMA, our open-science speech foundation model family for both ASR and ST in ๐Ÿ‡ฌ๐Ÿ‡ง English and ๐Ÿ‡ฎ๐Ÿ‡น Italian.

The models are live and ready to try on @hf.co:
๐Ÿ”— huggingface.co/collections/...

๐Ÿ“„ Preprint: arxiv.org/abs/2505.22759

#ASR #ST #OpenScience #MultilingualAI

30.05.2025 15:35 โ€” ๐Ÿ‘ 7    ๐Ÿ” 3    ๐Ÿ’ฌ 0    ๐Ÿ“Œ 0
Inline citations with only first author name, or first two co-first author names.

Inline citations with only first author name, or first two co-first author names.

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/...

29.05.2025 08:53 โ€” ๐Ÿ‘ 85    ๐Ÿ” 23    ๐Ÿ’ฌ 4    ๐Ÿ“Œ 0

I am honored to have received this award today! ๐ŸŽŠ

09.05.2025 16:17 โ€” ๐Ÿ‘ 4    ๐Ÿ” 0    ๐Ÿ’ฌ 0    ๐Ÿ“Œ 0

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! โฐ

Please email task organizers or the google group with any questions ๐Ÿฅณ

03.04.2025 15:27 โ€” ๐Ÿ‘ 6    ๐Ÿ” 4    ๐Ÿ’ฌ 0    ๐Ÿ“Œ 0

๐Ÿ“ข The evaluation period of the Instruction Following task at
@iwslt.bsky.social just started!

๐Ÿ–ฅ๏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)!
โžก๏ธ iwslt2025.speechm.cloud.cyfronet.pl

01.04.2025 12:39 โ€” ๐Ÿ‘ 9    ๐Ÿ” 5    ๐Ÿ’ฌ 0    ๐Ÿ“Œ 0

Thanks a lot! @deboranozza.bsky.social already added me to the channel ๐Ÿ˜Š

25.03.2025 15:50 โ€” ๐Ÿ‘ 2    ๐Ÿ” 0    ๐Ÿ’ฌ 0    ๐Ÿ“Œ 0

I'm thrilled to be one of the speakers at the next MT Marathon in Helsinki ๐Ÿš€

I look forward to sharing insights on automatic translation and related topics with our community!

19.03.2025 23:04 โ€” ๐Ÿ‘ 2    ๐Ÿ” 0    ๐Ÿ’ฌ 0    ๐Ÿ“Œ 0

โค๏ธ

17.03.2025 23:54 โ€” ๐Ÿ‘ 1    ๐Ÿ” 0    ๐Ÿ’ฌ 1    ๐Ÿ“Œ 0
Preview
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...

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! ๐Ÿ†“

arxiv.org/abs/2502.11946

20.02.2025 15:11 โ€” ๐Ÿ‘ 4    ๐Ÿ” 0    ๐Ÿ’ฌ 0    ๐Ÿ“Œ 1
Post image

As if you needed more reasons to submit to #GITT2025:
๐Ÿ”‘๐ŸŽต Cristina Anselmi, video game #localization & #AI expert with a focus on #inclusive #language will be our keynote speaker!
๐Ÿ’ธRegistration fees are on the MTSummit website and you can register just for GITT if you so choose ๐Ÿ˜Ž
๐Ÿ‘€ See you there! ๐Ÿ‘€

13.02.2025 15:10 โ€” ๐Ÿ‘ 13    ๐Ÿ” 9    ๐Ÿ’ฌ 0    ๐Ÿ“Œ 1
Preview
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...

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 ๐Ÿ‘

๐Ÿ“ƒ Preprint: arxiv.org/abs/2501.02370
โฐ Code will be released soon

#NLProc #Speech

23.01.2025 08:44 โ€” ๐Ÿ‘ 10    ๐Ÿ” 3    ๐Ÿ’ฌ 0    ๐Ÿ“Œ 0
Preview
a polar bear cub is laying in a pile of branches . ALT: a polar bear cub is laying in a pile of branches .

Hello world! ๐Ÿ‘‹ 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!

22.01.2025 12:17 โ€” ๐Ÿ‘ 27    ๐Ÿ” 15    ๐Ÿ’ฌ 0    ๐Ÿ“Œ 1

๐Ÿ™Œ All members of our group are now on Bluesky! ๐Ÿ™Œ

You can find all of us in this starter pack ๐Ÿ‘‡

16.01.2025 09:51 โ€” ๐Ÿ‘ 6    ๐Ÿ” 5    ๐Ÿ’ฌ 0    ๐Ÿ“Œ 0
Instruction-following Speech Processing track Home of the IWSLT conference and SIGSLT.

Exciting news: IWSLT will be co-located with @aclmeeting.bsky.social 2025 again this year! ๐ŸŽ‰

Interested in speech processing? Check out the new task on instruction following โ€” any model can participate! ๐Ÿš€

๐Ÿ“… Data release: April 1
โณ Submission deadline: April 15

๐Ÿ’ฌ iwslt.org/2025/instruc...

15.01.2025 18:36 โ€” ๐Ÿ‘ 11    ๐Ÿ” 5    ๐Ÿ’ฌ 0    ๐Ÿ“Œ 0

Iโ€™m glad to announce that our work โ€œHow "Real" is Your Real-Time Simultaneous Speech-to-Text Translation System?โ€ has been accepted at the Transactions of @aclmeeting.bsky.social (TACL)! ๐ŸŽ‰

The preprint is available here:
arxiv.org/pdf/2412.18495

27.12.2024 14:07 โ€” ๐Ÿ‘ 7    ๐Ÿ” 2    ๐Ÿ’ฌ 0    ๐Ÿ“Œ 0
Post image Post image

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:
๐Ÿ‘‰ MagneT: clic2024.ilc.cnr.it/wp-content/u...
๐Ÿ‘‰ GFG: clic2024.ilc.cnr.it/wp-content/u...

06.12.2024 16:22 โ€” ๐Ÿ‘ 9    ๐Ÿ” 2    ๐Ÿ’ฌ 0    ๐Ÿ“Œ 0
Preview
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.

๐ŸŒ Interested in Simultaneous Translation? We're organizing the IWSLT SimulST Shared Task and would love your input for the 2025 edition. ๐Ÿ—ฃ๏ธ

๐Ÿ“ Share your thoughts here: forms.gle/LwkF3284NzZd...

05.12.2024 16:57 โ€” ๐Ÿ‘ 4    ๐Ÿ” 1    ๐Ÿ’ฌ 0    ๐Ÿ“Œ 0
Post image

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

05.12.2024 10:40 โ€” ๐Ÿ‘ 20    ๐Ÿ” 4    ๐Ÿ’ฌ 1    ๐Ÿ“Œ 0
Dennis Fucci, Andrea Piergentili, and Luisa Bentivogli at CLiC-it 2024 | Machine Translation Unit

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!

04.12.2024 10:43 โ€” ๐Ÿ‘ 8    ๐Ÿ” 4    ๐Ÿ’ฌ 0    ๐Ÿ“Œ 0

Iโ€™ve created an Italian #NLProc Researcher Starter Pack ๐Ÿ‡ฎ๐Ÿ‡น

DM me to join if you're not in yet!

go.bsky.app/LHbWLHp

04.12.2024 17:04 โ€” ๐Ÿ‘ 24    ๐Ÿ” 5    ๐Ÿ’ฌ 0    ๐Ÿ“Œ 0
Post image Post image

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-...

02.12.2024 17:41 โ€” ๐Ÿ‘ 8    ๐Ÿ” 1    ๐Ÿ’ฌ 0    ๐Ÿ“Œ 0

@sarapapi is following 20 prominent accounts