Jan Švec | honzas.cz

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.

GitHub LinkedIn ORCID Google Scholar

On Speech Recognition Model Adaptation and Accuracy Calibration for Oral History Archives

September 24, 2026

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.

From Three Prompts to One: Two Years of AI in Teaching

September 1, 2026

AI in Education Large Language Models Speech Technology

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.

From UWebASR to calibrated accuracy estimates for oral histories

July 3, 2026

Applied AI Speech Technology Agentic AI Digital Humanities

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.

At the National Final of the Czech AI Olympiad

June 22, 2026

AI in Education Mentoring Community

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.

An Unforgettable Memory Day at Vinohrady with DigiDiaDem

June 18, 2026

DigiDiaDem Cognitive Screening Speech Technology

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.

Forecasting cross-border power transit: a bachelor thesis developed with ČEPS

June 16, 2026

AI in Education Machine Learning Industry Cooperation

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.

Do not buy AI, download it. But clean up your data first.

June 10, 2026

Applied AI Large Language Models Software Development

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.

LLM-Based Metadata Extraction from NATO Scanned Documents

June 2, 2026

Large Language Models Digital Humanities

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.

AI in education, companies and biotechnology

27-28 April 2026

Applied AI AI in Education Biotechnology Community

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.

Agentic AI for Digital Humanities

26 April - 12 May 2026

Applied AI Large Language Models Digital Humanities

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.

Transforming Education of Internet Technologies Through Generative AI and Industry Cooperation

April 23, 2026

AI in Education Industry Cooperation

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.

Judging the Škrábej, kotě! Competition

April 17, 2026

AI in Education Community

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.

Context-aware synthetic promoter design using neural networks enables rewiring of eukaryotic transcriptional networks

March 17, 2026

Machine Learning Biotechnology

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.

The DigiDiaDem Speech-Cognitive Dataset: Initial Experiments on Detecting Cognitive Impairments From Speech

February 6, 2026

DigiDiaDem Cognitive Screening Speech Technology Machine Learning

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.

SpecKit: structured AI-assisted software development

January 28, 2026

Applied AI Software Development

AI coding assistants can produce code quickly, but speed does not replace clear requirements and architecture. SpecKit turns an initial idea into a specification, an implementation plan and a visible set of tasks. The workshop shows how this structure helps keep research prototypes and applied software understandable while they evolve.

Internet Technologies with generative AI, hardware prototypes and an industry customer

January 26, 2026

AI in Education Industry Cooperation Software Development

Internet technologies become easier to understand when students have to connect sensors, backend services and a customer-facing interface into one working system. In the 2025/2026 winter semester, five teams in our Internet Technologies course developed warehouse-monitoring prototypes with an API and project requirements prepared by Aimtec. Generative AI supported both the student projects and our teaching materials, with transparent reporting of the tools used and an individual defence of each submitted solution.

Home