stek_fbk

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 ...

🚀 Join us for the LT@FBK day 2025!
Discover cutting-edge research and highlights in speech and language technologies from FBK.

📅 October 28, 2025
📍 FBK, Trento
Details and registration:
www.fbk.eu/en/event/346...

The SpeechTek Lab is at @interspeech.bsky.social in forces this year. If you want to hear about our works on multiligual ASR, low-resourced languages, efficient architectures and pathological speech, you will find us around.

We have an open position on resource-aware and dynamic speech processing within the IPCEI-CIS project. It is about cutting edge ML applied to speech processing. It will be fun. Details:https://shorturl.at/E4DXR
DM me for any request. #ASR #speechprocessing #AI #ML

@interspeech.bsky.social is an important venue for us. This year the SpeechTechLab will present 5 papers, two of which thanks to the @eloquenceai.bsky.social project.
Many thanks to our awesome young leading authors: Umberto Cappellazzo, Seraphina Fong, Daline Marx and Abdul Hannan

We are funding 1 PhD grant on advancing conversational and understanding capabilities of speechLLM systems.
phd.fbk.eu/calls/detail...

Deadline May 12th:
iecs.unitn.it/education/ad...

DM me for further info

Sharing the red carpet with @luisabentivogli.bsky.social @fbk-mt.bsky.social

@alessiobrutti.bsky.social is on the red carpet on his way to the Assembly of Members of the Alliance for Language Technology #ALTEDIC and the kick off of the LLMs4EU project: towards preserving our cultural and language diversity and giving european citizens open and ethical #languagetechnologies

The Speerch Technology Lab grows bringing in fresh energy from two new young talents. @sharpii.bsky.social and Lorenzo will advance our tools for speech and language technologies, contributing to @eloquenceai.bsky.social, Meetween and the ALT-EDIC projects.

If you are working on learning-based approaches for (multiple) sound source localization and tracking, keep in mind our special session at
@eusipco2025.
Submission deadline: March 1st
Track: 20.6
Submission link: eusipco2025.org/submit-your-...

After 40 months of excellent research, on Jan 15th @Umberto_Senpai successfully completed his PhD journey. Umberto was definitely among our top students with several high-level publications and collaborations with top-notch labs. Congratulations Umberto🎉🎉🎉

Large Language Models Are Strong Audio-Visual Speech Recognition Learners Multimodal large language models (MLLMs) have recently become a focal point of research due to their formidable multimodal understanding capabilities. For example, in the audio and speech domains, an ...

The two papers are:
- Large Language Models Are Strong Audio-Visual Speech Recognition Learners arxiv.org/abs/2409.12319
- EFL-PEFT: A communication Efficient Federated Learning framework using PEFT sparsification for ASR

2025 just started and we've got:
- 2 papers accepted at ICASSP
- 2 ALT-EDIC projects and 1 HE project kicking off in weeks
Let's hope it continues in this way🤞😎

It was a great experience presenting the research results of the @speechtekfbk.bsky.social lab at the opening ceremony of the doctoral school of electronic engineering at UTEM in Santiago de Chile. Many thx to Ali for inviting me: it was lovely.

The speech tech lab at Fondazione Bruno Kessler is here too!