News

From June 9 to August 1, 2025, the Faculty of Information Technology of Brno University of Technology will serve as the venue for the gathering of dozens of leading global experts in the field of speech and language technologies. The 32nd edition of the prestigious Jelinek Summer Workshop on Speech and Language Technology (JSALT) is organized by Johns Hopkins University (Maryland, USA), this year in cooperation with partners of the European ESPERANTO project. This edition is co-organized by FIT BUT and the company Phonexia, with the support of OP JAK (Operational Programme Johannes Amos Comenius) and under the patronage of the City of Brno and the South Moravian Region. For our faculty, this is a major recognition, closely related to the long-term and internationally highly successful work of the BUT Speech@FIT research group.

The workshop itself will be preceded by a summer school from June 9 to June 20, offering lectures on topics related to speech technologies and natural language processing filled with practical sessions and hand-on. The lectures will be also available to the broader public interested in the field as video-stream on YouTube. The content of the summer school will be presented by the senior participants of the workshop and invited experts.

The six-week research workshop itself (June 23 – August 1) will host more than 100 researchers from around the world, including prominent figures such as Ricard Marxer (University of Toulon), Ramani Duraiswami (University of Maryland), Samuele Cornell (Carnegie Mellon University), Yannick Estève (Laboratoire d'Informatique d'Avignon) and Fethi Bougares (Elyadata). Participants are divided into four teams, each focusing on a selected research topic. Two of the teams are led by researchers from FIT BUT: Assoc. Prof. Lukáš Burget and Dr. Santosh Kesiraju. For this year’s edition, the following core topics have been selected by community and sponsors:

• Play your Part: Towards LLM role-playing agents that stick to their role
• Advancing Expert-Level Reasoning and Understanding in Large Audio Language Models
• End to End Multi-Channel Multi-Talker ASR, EMMA
• TTS4ALL: TTS in Low Resource Scenarios – Data Management, Methodology, Models, Evaluation

The workshop’s goal is not only to push the boundaries of research once again, but also to foster international scientific collaboration and involve students at all levels. Each team includes senior researchers, PhD students, and undergraduate students, providing an exceptional opportunity for expert mentoring. A key criterion for workshop outcomes is also the openness of results, particularly in terms of open-source contributions.

The workshop is named after Bedřich/Frederick Jelinek (1932–2010), a Czech-American scientist from Kladno and a pioneer in speech recognition research, who for many years led the Center for Language and Speech Processing at Johns Hopkins University. It is therefore symbolic that this event bearing his name will be held at FIT BUT, a faculty that – thanks to the contributions of figures such as Hynek Heřmanský, Jan Černocký, and Lukáš Burget – has become one of the world's leading centers in AI and machine learning for speech data mining.

Thinking about pursuing a Ph.D. at FIT and need more information? Join us on April 8 in lecture hall D 206 where a presentation about the Ph.D. by Professor Sekanina will be given at 3 pm. This will be followed by a discussion with academics, whom you can ask about anything you are interested in regarding PhD studies.

Information about doctoral studies can also be found on the website. An overview of the dissertation topics is available here. And a reminder, the deadline for applications (Round 1) is 30 May.

The 10th anniversary edition of HiVisComp brought together an informal and inspiring gathering of computer graphics, image processing and computer vision experts. The conference was founded in 2014 by Martin Čadík (FIT BUT) and Jaroslav Křivánek (MFF UK). Since then, the event has come a long way and grown significantly. Over the years, it has featured 30 invited speakers from 13 countries, presented 121 technical papers and received almost 1000 abstracts. Today, Martin Čadík organizes it with the help of colleagues from CTU.

HiVisComp was held this year in the Krkonoše Mountains from 29 January to 1 February and once again combined scientific lectures, exchange of experiences and sporting activities. In the current edition, participants discussed the latest developments in data visualisation, lighting simulation or innovative image processing methods. Among the highlights of the programme were the invited lectures, featuring, for example, Gabriela Csurka from NAVER LABS Europe, who presented the evolution from the CroCo model to the DUSt3R and MASt3R, which have brought a major shift in the field of 3D computer vision. She showed how these methods unify and simplify the processing of 3D visual data and open up new possibilities for tasks such as visual localization without a map or robotic navigation.

Torsten Sattler from CTU presented the 3D Gaussian Splatting method, which enables faster and higher quality 3D scene reconstruction compared to traditional approaches. He focused on artifact resolution, working with different lighting conditions and extracting accurate 3D models.

Marc Alexa from TU Berlin presented a new approach to fitting lines to planes and related problems. His method is computationally efficient, easy to implement and preserves important geometric properties.

As part of the research team presentation, Adam Herout from FIT BUT presented The Malleable Glyph Challenge.

Outdoor and social activities are an integral part of this conference. This year, they were in the spirit of cross-country skiing and skiing. The full conference programme can be viewed on hiviscomp.cz.