Jan Hajič
Assistant Professor at Institute of Formal and Applied Linguistics, Charles University
Prague, Prague, Czechia
Summary
👤
Senior🎓
Top SchoolJan Hajič is an assistant professor and head of the Prague Music Computing Group at Charles University, combining 11 years of experience in computational musicology, NLP, and machine learning to lead projects such as OmniOMR (optical music recognition) and the DACT chant analytics workstream. He built one of the first fully machine-learnable pipelines for music notation recognition and created a substantial dataset that jumpstarted ML-based OMR research, while also contributing to open-source tooling such as gensim. Jan blends rigorous digital scholarship—having produced a digital edition of the Jistebnice Kancionál and applied bioinformatics methods to Gregorian chant—with active performance as a professional harpsichordist and ensemble director. He supervises doctoral and undergraduate researchers, fosters transdisciplinary collaborations through the TAH Centre, and consults on projects ranging from music generation to medical text processing and authorship attribution. Notably, his profile bridges deep technical expertise and live musical practice, enabling unique research questions at the intersection of sound, notation, and computation.
11 years of coding experience
6 years of employment as a software developer
Mgr., Mathematical Linguistics, Mgr., Mathematical Linguistics at Charles University in PragueBachelor's degree, Teorie a provozovací praxe staré hudby - cembalo, Bachelor's degree, Teorie a provozovací praxe staré hudby - cembalo at Masarykova univerzita BrnoMaster of Arts - MA, Harpsichord, Master of Arts - MA, Harpsichord at Janáčkova akademie múzických umění v BrněPhD, Natural Language Processing, PhD, Natural Language Processing at Charles University
Github Skills (11)
machine-learning10
gensim10
python10
data-science10
numpy10
natural-language-processing9
scipy9
topic-modeling9
unit-testing8
data-mining8
documentation8
Programming languages (3)
Github contributions (5)
piskvorky/gensim
Jan 2015 - Apr 2015
Topic Modelling for Humans
Role in this project:
Data Scientist
Data ScientistContributions:11 commits, 2 PRs, 2 comments in 2 months
Contributions summary:Jan primarily contributed to the `ShardedCorpus` class, focusing on its documentation, functionality, and testing. Their commits demonstrate improvements to the class documentation, making it more tutorial-like, and they also modified the test suite to enhance its capabilities, including support for Python 2.6 compatibility. The user's work also included fixing a warning issue within the setup process, indicating their involvement in the project's overall structure.
pythonword-similarityword-embeddingsdata-miningfor-humans
hajicj/MUSCIMarker
Aug 2016 - Oct 2018
Contributions:1 release, 383 commits, 4 PRs in 2 years 3 months
musicalscores
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.