BUT Speech
@butspeech.bsky.social
We do impactful research and raise new leading scientific personalities in the field of speech processing.
Alex Polok has started an internship at CMU’s
WAV Lab @wavlab.bsky.social , 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.
WAV Lab @wavlab.bsky.social , 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.
January 16, 2026 at 10:24 PM
Alex Polok has started an internship at CMU’s
WAV Lab @wavlab.bsky.social , 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.
WAV Lab @wavlab.bsky.social , 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: www.fit.vut.cz/fit/info/dd/...
MS-Teams: teams.microsoft.com/l/meetup-joi...
📍 FIT BUT, G108 or 💻 via MS Teams.
Official announcement & abstract: www.fit.vut.cz/fit/info/dd/...
MS-Teams: teams.microsoft.com/l/meetup-joi...
January 13, 2026 at 9:33 AM
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: www.fit.vut.cz/fit/info/dd/...
MS-Teams: teams.microsoft.com/l/meetup-joi...
📍 FIT BUT, G108 or 💻 via MS Teams.
Official announcement & abstract: www.fit.vut.cz/fit/info/dd/...
MS-Teams: teams.microsoft.com/l/meetup-joi...
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 😼
January 12, 2026 at 1:00 PM
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:
www.linkedin.com/feed/update/...
www.linkedin.com/feed/update/...
January 12, 2026 at 12:59 PM
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:
www.linkedin.com/feed/update/...
www.linkedin.com/feed/update/...
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.
Homepage
Where AI’s brightest minds connect to exchange ideas, challenge perspectives, and shape the future of artificial intelligence.
ai-nexus.mbzuai.ac.ae
January 5, 2026 at 9:38 PM
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.
All the best for 2026 from the Brno crew!
January 5, 2026 at 9:37 PM
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!
December 8, 2025 at 7:49 PM
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!
December 7, 2025 at 2:28 PM
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/j...
vgs-it.fit.vutbr.cz/2025/11/04/j...
December 4, 2025 at 2:04 PM
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/j...
vgs-it.fit.vutbr.cz/2025/11/04/j...
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.
December 3, 2025 at 3:42 PM
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-web...
www.isca-archive.org/interspeech_...
landing.signalprocessingsociety.org/ieee-sps-web...
www.isca-archive.org/interspeech_...
November 20, 2025 at 10:24 AM
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-web...
www.isca-archive.org/interspeech_...
landing.signalprocessingsociety.org/ieee-sps-web...
www.isca-archive.org/interspeech_...
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! www.cnaip.cz/en/czech-ai
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! www.cnaip.cz/en/czech-ai
Czech AI — CNAIP
Czech AI. One Map, the Complete Czech AI Ecosystem. Explore an overview of all the key players in the domestic AI market
www.cnaip.cz
October 20, 2025 at 3:43 PM
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! www.cnaip.cz/en/czech-ai
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! www.cnaip.cz/en/czech-ai
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?lis...
July 24, 2025 at 8:38 AM
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?lis...
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?lis...
jsalt2025.fit.vut.cz/plenary-lect...
jsalt2025.fit.vut.cz/plenary-lect...
July 22, 2025 at 9:04 AM
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?lis...
jsalt2025.fit.vut.cz/plenary-lect...
jsalt2025.fit.vut.cz/plenary-lect...
Today, July 18, at 11:00, Herve Bredin [pyannoteAI, France] will give the 5th Plenary talk at the JSALT workshop "Speaker diarization, a love loss story", see jsalt2025.fit.vut.cz/plenary-lect... for details.
July 18, 2025 at 9:02 AM
Today, July 18, at 11:00, Herve Bredin [pyannoteAI, France] will give the 5th Plenary talk at the JSALT workshop "Speaker diarization, a love loss story", see jsalt2025.fit.vut.cz/plenary-lect... for details.
📢 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: www.youtube.com/playlist?lis... 🎤📺
jsalt2025.fit.vut.cz/plenary-lect...
jsalt2025.fit.vut.cz/plenary-lect...
July 1, 2025 at 8:33 AM
📢 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: www.youtube.com/playlist?lis... 🎤📺
jsalt2025.fit.vut.cz/plenary-lect...
jsalt2025.fit.vut.cz/plenary-lect...
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.
www.mff.cuni.cz/en/research-...
www.mff.cuni.cz/en/research-...
May 28, 2025 at 3:43 PM
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.
www.mff.cuni.cz/en/research-...
www.mff.cuni.cz/en/research-...
We have great pleasure to invite you to a talk of an excellent Czech scientist, Professor at #EPFL, Lenka Zdeborová. We have never seen a talk treating machine learning as a problem of statistical physics! Tuesday, May 20, 2025 at 13:00 in lecture room E112 and online www.youtube.com/live/FCvPhHm...
May 19, 2025 at 4:11 PM
We have great pleasure to invite you to a talk of an excellent Czech scientist, Professor at #EPFL, Lenka Zdeborová. We have never seen a talk treating machine learning as a problem of statistical physics! Tuesday, May 20, 2025 at 13:00 in lecture room E112 and online www.youtube.com/live/FCvPhHm...
Several speech students participated at the FIT Conference of innovations, technology and science - Excel@FIT. Congratulations to Sathvik, Dominik, and Ondrej for winning Excel prizes!
excel.fit.vutbr.cz/vysledky/
excel.fit.vutbr.cz/vysledky/
May 9, 2025 at 8:05 AM
Several speech students participated at the FIT Conference of innovations, technology and science - Excel@FIT. Congratulations to Sathvik, Dominik, and Ondrej for winning Excel prizes!
excel.fit.vutbr.cz/vysledky/
excel.fit.vutbr.cz/vysledky/
Congratulations to Lin Zhang for her new post-doc position at CLSP at Johns Hopkins University! She is working on anti-spoofing and anonymization with Nicholas Andrews and Matthew Wiesner. She also collaborates closely with Sanjeev Khudanpur, Leibny Paola García-Perera, and Kevin Duh.
May 9, 2025 at 5:26 AM
Congratulations to Lin Zhang for her new post-doc position at CLSP at Johns Hopkins University! She is working on anti-spoofing and anonymization with Nicholas Andrews and Matthew Wiesner. She also collaborates closely with Sanjeev Khudanpur, Leibny Paola García-Perera, and Kevin Duh.
Over the weekend we to plan for the upcoming #JSALT25 workshop for the topic "Advancing Expert-Level Reasoning and Understanding in Large Audio Language Models". Two days of intense brain storming 🧠 and planning powered by extra portions of coffee ☕️.
jsalt2025.fit.vut.cz/summer-works...
jsalt2025.fit.vut.cz/summer-works...
May 9, 2025 at 5:25 AM
Over the weekend we to plan for the upcoming #JSALT25 workshop for the topic "Advancing Expert-Level Reasoning and Understanding in Large Audio Language Models". Two days of intense brain storming 🧠 and planning powered by extra portions of coffee ☕️.
jsalt2025.fit.vut.cz/summer-works...
jsalt2025.fit.vut.cz/summer-works...
Glad to announce another married man in the group - Pradyoth's wedding with Sameeksha took place in Mangalore on Thu 3rd April (before ICASSP) in presence of 3.5k guests! All the best!
April 25, 2025 at 7:44 AM
Glad to announce another married man in the group - Pradyoth's wedding with Sameeksha took place in Mangalore on Thu 3rd April (before ICASSP) in presence of 3.5k guests! All the best!
The networking activities around ICASSP continued after Meeami: on Monday 7 April, Honza took part in an official visit to IIIT Hyderabad, met its director and spent nice time with Anil Kumar Vuppala and his colleagues and students in Language Technologies Research Center (LTRC).
April 25, 2025 at 7:43 AM
The networking activities around ICASSP continued after Meeami: on Monday 7 April, Honza took part in an official visit to IIIT Hyderabad, met its director and spent nice time with Anil Kumar Vuppala and his colleagues and students in Language Technologies Research Center (LTRC).
The Speech@FIT research group continues its industry collaboration at global scale, with Santosh and Alex recently visiting Meeami Technologies in Hyderabad.
April 7, 2025 at 6:55 AM
The Speech@FIT research group continues its industry collaboration at global scale, with Santosh and Alex recently visiting Meeami Technologies in Hyderabad.
Our papers to be presented at ICASSP in Hyderabad!
Target Speaker ASR with Whisper, ieeexplore.ieee.org/document/108...
Introduces a novel approach to training target-speaker ASR systems utilizing frame-level diarization outputs.
Apr 11: 2:00 pm - 3:30 pm, Poster 2E, presented by Alexander Polok
Target Speaker ASR with Whisper, ieeexplore.ieee.org/document/108...
Introduces a novel approach to training target-speaker ASR systems utilizing frame-level diarization outputs.
Apr 11: 2:00 pm - 3:30 pm, Poster 2E, presented by Alexander Polok
April 2, 2025 at 1:20 PM
Our papers to be presented at ICASSP in Hyderabad!
Target Speaker ASR with Whisper, ieeexplore.ieee.org/document/108...
Introduces a novel approach to training target-speaker ASR systems utilizing frame-level diarization outputs.
Apr 11: 2:00 pm - 3:30 pm, Poster 2E, presented by Alexander Polok
Target Speaker ASR with Whisper, ieeexplore.ieee.org/document/108...
Introduces a novel approach to training target-speaker ASR systems utilizing frame-level diarization outputs.
Apr 11: 2:00 pm - 3:30 pm, Poster 2E, presented by Alexander Polok