Korbinian Riedhammer
Full Professor at Technische Hochschule Nürnberg Georg Simon Ohm
Nuremberg, Bavaria, Germany
Summary
👤
Senior🎓
Top SchoolKorbinian Riedhammer is a Full Professor and entrepreneur with 14 years of experience at the intersection of software architecture, machine learning and speech technology. He leads academic teaching and research on sequence learning, large-vocabulary ASR, scalable keyword search and spoken language understanding while also founding two companies that translate research into products. A long-time contributor to the influential Kaldi ASR project, he implemented core tied-GMM components and helped extend support for full covariance models—work that underpins many production speech systems. His background includes impactful research stints at ICSI and contributions to large-scale government intelligence and defense programs, reflecting experience with high-stakes deployments. Based in Nuremberg, he blends rigorous PhD-level research (summa cum laude) with hands-on engineering and UX sensibilities. Colleagues describe him as someone who moves smoothly between theoretical advances and pragmatic system design to deliver scalable speech solutions.
14 years of coding experience
6 years of employment as a software developer
JMF GymnasiumDiplom, Computer Science, Diplom, Computer Science at FAU Erlangen-NürnbergDoktor-Ingenieur (Ph. D.), Computer Science, summa cum laude, Doktor-Ingenieur (Ph. D.), Computer Science, summa cum laude at University of Erlangen-Nuremberg
German, English
Github Skills (7)
kaldi10
speech-recognition10
c-language10
cprogramming-language10
gmm10
machine-learning8
cuda6
Programming languages (12)
Github contributions (5)
kaldi-asr/kaldi
May 2015 - Sep 2020
kaldi-asr/kaldi is the official location of the Kaldi project.
Role in this project:
Back-end Developer
Back-end DeveloperContributions:2 PRs, 32 comments in 5 years 5 months
Contributions summary:Korbinian contributed to the Kaldi project by implementing and modifying core components related to tied Gaussian mixture models (GMMs), which are central to speech recognition systems. Their work included the initial creation of tied-GMM-related code, adding a unit test for the am-tied-diag-gmm, and refactoring full-GMM to use the Accumulator and Update functions. The user also contributed to further development in support of full covariance matrices.
cudakaldiasrspeech-to-textkaldi-asr
ohm-softa/03-inheritance
Mar 2019 - Oct 2023
Contributions:12 pushes, 2 branches in 4 years 8 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.