Danijel Korzinek
Senior Researcher at Silver Bullet Solutions Sp. z o. o.
Warsaw, Masovian Voivodeship, Poland
Summary
👤
Senior🎓
Top SchoolDanijel Korzinek is a Senior Researcher and speech technologies specialist with 13 years of experience focused on speech recognition, telephony, and datamining. He holds a PhD in Computer Science and combines academic research with industry consulting roles at iQor and Silver Bullet Solutions, bridging prototype research and production deployments. His contributions to the Kaldi ASR codebase—fixing Java online audio clients and server compatibility issues—highlight practical expertise in integrating open-source speech tooling into real-world telephony systems. Based in Warsaw, he has driven Polish speech corpora development and applied ViaVoice-era research to modern machine learning pipelines, making him adept at both low-level audio processing and higher-level ML model work. Notably, he maintains a long-term presence at the Polish-Japanese Academy of IT, reflecting a sustained commitment to research and mentoring alongside commercial projects.
12 years of coding experience
16 years of employment as a software developer
M.Sc., Computer Science, M.Sc., Computer Science at Polish-Japanese Academy of Information TechnologyDoctor of Philosophy (PhD), Computer Science, Doctor of Philosophy (PhD), Computer Science at Polsko-Japońska Wyższa Szkoła Technik Komputerowych w Warszawie
Croatian, Polish, English, German
Github Skills (7)
javas10
java10
speech-recognition9
c-language8
cprogramming-language8
cuda7
shell6
Programming languages (10)
Github contributions (5)
kaldi-asr/kaldi
May 2021 - May 2021
kaldi-asr/kaldi is the official location of the Kaldi project.
Role in this project:
Back-end Developer
Back-end DeveloperContributions:1 commit, 7 PRs, 61 comments in 1 day
Contributions summary:Danijel primarily contributed to the Java-based online audio client, adding copyright notices to the code and fixing compatibility issues with Java versions prior to 1.7. They also fixed the online audio server and client programs by removing confidence calculation, and fixed indentation. Their work involved modifying core functionalities and dependencies within the online audio server, and also fixing text matrix parsing code.
cudakaldiasrspeech-to-textkaldi-asr
danijel3/KaldiJava
Jun 2016 - Oct 2016
Contributions:13 commits, 10 pushes, 2 branches in 3 months
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.