BUT Speech

Bio-inspired VGS-IT talk next week. Giulia D’Angelo “What’s catching your eye? – Event-driven sensing & neuromorphic computing for active vision” 🗓 Thu, Mar 26, 14:00 📍 Room A113 (FIT BUT) / YouTube Abstract below: vgs-it.fit.vutbr.cz/2026/03/13/giu…

Alex Polok has started an internship at CMU’s @WavLab (LTI), continuing DiCoW research on diarization-conditioned target-speaker ASR with Whisper (JSALT 2025). Next: extending to SpeechLLMs (DiXtral) and joint diarization + TS-ASR toward end-to-end speaker-aware models.

Ladislav Mošner will defend his PhD dissertation “Far-Field Speaker Verification Incorporating Multichannel Processing” on Wed 14 Jan at 09:00 CET. 📍 FIT BUT, G108 or 💻 via MS Teams. Official announcement & abstract: fit.vut.cz/fit/info/dd/20… MS-Teams: teams.microsoft.com/l/meetup-join/…

Exam period is in full swing at our Faculty of IT 📚 On Fri, Jan 9, over 500 2nd-year bachelor students took the Signals & Systems (ISS) exam. Honza promised reference fixes… but seems he delegated them (again!) to his cat Kaja 😼

On Jan 13, Prachi Singh will give an online talk on Speaker Diarization as part of a Faculty Development Programme by UPES, Dehradun 🇮🇳. The session covers current trends with hands-on insights. See the LinkedIN page for details: linkedin.com/feed/update/ur…

Honza will be speaking at the 2nd MBZUAI Speech & NLP Symposium in Abu Dhabi, organized by Hanan Aldarmaki, Bashar Alhafni, Preslav Nakov and Thamar Solorio from the Mohamed bin Zayed University of Artificial Intelligence. ai-nexus.mbzuai.ac.ae/?panel=2nd%20M…

All the best for 2026 from the Brno crew !

After presenting at USC (thanks Shri Narayanan), Alex Polok & Sathvik Udupa are sharing their ASRU posters in Honolulu on Dec 8. 10:30-12:00 and 14:00-15:30 respectively. Don’t miss them—and Sara Barahona presenting our VoxCeleb work too!

Hynek Heřmanský received the 2025 Czech AI Award at Vzlet, Prague! Born in Nové Město na Moravě, with a career spanning OGI, JHU and Google, he’s known for RASTA/PLP and early NN advocacy. Congrats to Hynek and thanks to Czech AI Platform & JIC!

Last week we welcomed Prof. Jan G. Švec for a great talk on how the human voice works—from source-filter basics to advanced biomechanics. Big thanks to FIT BUT’s Students’ Union for the venue and A/V support! vgs-it.fit.vutbr.cz/2025/11/04/jan…

Great news from Phonexia: new growth chapter with Crescendo Equity Partners as 100% owner! Founded in 2006 by 6 Speech@FIT members, Phonexia will see accelerated expansion and R&D investment in speech tech for security/defense and business sectors.

Lin Zhang, longtime Brno collaborator now at JHU, will present the IEEE SPS talk on partially fake speech on Nov 20, 2025, 9:30 AM ET. Also see her Interspeech paper “PartialEdit.” landing.signalprocessingsociety.org/ieee-sps-webin… isca-archive.org/interspeech_20…

The Czech National AI Platform is a joint initiative of the public, private, and non-profit sectors. BUT Speech@FIT is proud to be a part of it. We recommend also having a look at the other Czech AI companies and University labs! cnaip.cz/en/czech-ai

We're wrapping up the #JSALT2025 workshop this Thu & Fri with team presentations after 8 weeks of work in Brno! Join us in person (D105 @ FIT) or online. Full agenda: jsalt2025.fit.vut.cz/summer-workshop. Don’t miss Sanjeev’s summary Thu morning: “How we got here and what we discovered”!

Details in #7" target="_blank" rel="nofollow noopener">jsalt2025.fit.vut.cz/plenary-lectur…

Thu July 24 11:00, we will have the last plenary talk of #JSALT2025 - Jordan Boyd-Graber Ying [University of Maryland] will present "Helpful AI Models: You can't always get what you want, but you might get what you need”" You can also watch it on YT: youtube.com/playlist?list=…

Tue July 22 11:00, we will have another plenary talk of #JSALT2025 - Xavier Serra [UPF Barcelona] will speak about Methodologies for Music Understanding and Generation in the Context of Trustworthy AI. You can also watch it on YT: youtube.com/playlist?list=… #6" target="_blank" rel="nofollow noopener">jsalt2025.fit.vut.cz/plenary-lectur…

📢 Barbara Schuppler (TU Graz) gives the 2nd #JSALT plenary tomorrow, Tue July 1, 11:00 in Room E112: "Cross-layer models for conversational speech recognition in low-resourced scenarios". Join in person or on YouTube: youtube.com/playlist?list=… 🎤📺 #2" target="_blank" rel="nofollow noopener">jsalt2025.fit.vut.cz/plenary-lectur…

Our paper "Diarization-conditioned Whisper for target speaker automatic speech recognition” is out and the highlights include exploring various ways to biasing Whisper for target speaker ASR. The paper is available free of charge from ScienceDirect: authors.elsevier.com/a/1lI9m_K8BYum…

Honza is giving a lecture at Charles University in Prague (Faculty of Mathematics and Physics, MFF) today. If you want to attend, note that it takes place in the new buildings of MFF in Troja, not the historical one in Mala Strana. mff.cuni.cz/en/research-an…