I work at the intersection of AI, speech technologies, language, and real-world systems.
At the Faculty of Applied Sciences, University of West Bohemia in Pilsen, I research and teach applied AI, speech and language technologies, LLMs, RAG, agentic AI workflows, and digital humanities. I also serve as the faculty representative for artificial intelligence. I bring together experience from research and practical projects for commercial companies.
Scanned archival collections are difficult to explore when full text and consistent metadata are missing. Our contribution at CLARIN, DARIAH & Libraries 2026 showed how we use large language models as a team to transcribe and enrich NATO archival documents. We presented the path from source scans to linked research materials, including researcher feedback and the limits of generated descriptions.
Students need real assignments, responsibility and feedback from people in industry. At Smart Region Forum 2026 on 22 October in Plzeň’s TechTower, I joined Jiří Dobrý from Aimtec to present our teaching cooperation at FAV ZČU. We traced a path from a semester project through AimtecHackathon to graduates working in industry.
Large oral-history collections become searchable once speech is converted into time-aligned text, yet researchers still need a practical way to judge transcript reliability. At DHECC 2026 in Odense on 24 September, I presented our paper on adapted speech-recognition models and calibrated accuracy estimates for six languages, co-authored with Jan Lehečka and Pavel Ircing. Conference attendees can find the presentation here together with direct links for using UWebASR in a browser, through BAS, with an AI assistant, via APIs or on offline HPC infrastructure.
Preparing study materials from a recorded lecture is a good example of work that generative AI has simplified substantially in a short time. Two years ago, I manually moved the recording, transcript, slides, and three core prompts between separate tools. Today, one instruction can turn a recording and its slides into a checked summary, material discussed beyond the presentation, a glossary, and a finished PDF for students.
Automatic speech recognition is most useful when users can also estimate how much trust to place in its output. For long witness testimonies, including Holocaust survivor testimonies, this matters because researchers often work with sensitive, historically valuable material. Agentic AI helped us turn a proof-of-concept workflow into a deployable production feature in roughly two weeks.
AI education becomes tangible when secondary-school students can develop their own solutions and defend them in front of an expert jury. The national final of the Czech AI Olympiad brought this energy to the Faculty of Applied Sciences in Plzeň on 22 June 2026. As an AI ambassador, I guided accompanying teachers around the faculty, gave them a lecture on AI in education and later joined the Public Administration jury.
Concern about memory can begin a long search for someone who will connect individual examinations and recommend the right next step. At Nezapomenutelný den paměti na Vinohradech, the DigiDiaDem team used an anonymised story resembling the Czech tale of the Little Hen and the Little Rooster to show how fragmented that journey can become. The case also demonstrated how a short digital prescreening can complement a standard assessment without replacing a clinical diagnosis.
Energy systems offer student projects a demanding combination of physical processes, changing conditions and large public datasets. I supervised Martin Horešovský's bachelor thesis on forecasting cross-border electricity transit, developed with external consultant Petr Souček from ČEPS. Martin defended the thesis with the highest grade on 16 June 2026, after taking first place in the bachelor section of the Faculty of Applied Sciences Student Conference.
Open models have made artificial intelligence more accessible, but useful deployment still depends on data, integration and honest evaluation. It was a pleasure to bring this practical perspective to the general public at Inovujeme Plzeň 2026 Next Level and to appear alongside such a strong group of speakers. I thank SIT Port for the organisation and for creating a lively workshop setting at TechTower.
Historical archives contain valuable evidence, but scanned documents are difficult to search when their metadata is incomplete or inconsistent. At the C4DHI Anniversary Workshop, I presented a workflow that uses large language models to extract structured metadata from scanned NATO archival documents. The talk focused on noisy OCR, multilingual records and the need to preserve evidence for human review.
Artificial intelligence is moving into education, engineering and biotechnology, but each field asks different questions about usefulness and responsibility. In the Naučíme AI podcast, I discussed how people can work with AI without reducing the subject to a single chatbot. The conversation connects university teaching, company adoption and interdisciplinary research through practical examples.
Complex research tasks do not fit into a single prompt: they need tools, intermediate checks and an inspectable sequence of steps. These workshop materials introduce agentic AI as a workflow for digital humanities and archival research. They connect an Oxford research stay, CLARIN collaboration and practical work with NATO archival documents.
Students need opportunities to use generative AI inside complete engineering projects where technical decisions remain visible and defensible. At the Trinational Round Table on Artificial Intelligence on 23 April 2026, I presented our Internet Technologies course built around cooperation with Aimtec, makerspace prototyping and transparent AI use. The talk connected AI-supported teaching materials, student-built IoT systems and individual verification that each student understands the submitted solution.
Programming competitions give children a reason to explain how an idea became a working project. At the final of the eighth Škrábej, kotě! competition at Centrum robotiky in Plzeň, I served on the jury and enjoyed listening to girls and boys talk about their first steps in programming. I am curious whether I will meet some of them again one day at AimtecHackathon.
Synthetic biology needs better ways to design regulatory DNA while reducing the number of laboratory experiments. Our article in npj Systems Biology and Applications uses neural networks to find context-aware locations for inserting transcription-factor binding sites into promoters. The result connects machine-learning model design with biological constraints and experimental validation.
Speech-based research into cognitive impairment needs datasets that connect carefully designed tasks, clinical context and reproducible evaluation. Our IEEE Access article introduces the DigiDiaDem Speech-Cognitive Dataset and the first experiments built on it. The work links dialogue-system design, speech recognition, data preparation and machine-learning evaluation within one research workflow.
