Dmytro Tkanov
Director, ASR Modeling at SoundHound AI
Berlin, Germany
Summary
🤩
Rockstar🎓
Top SchoolDmytro Tkanov is a Director of ASR Modeling based in Berlin with over a decade of hands-on experience in speech processing, acoustic modeling, and machine learning. He has progressed from sound analysis engineer to senior technical and managerial roles at SoundHound AI, shaping ASR architecture and leading cross-functional teams to productionize speech systems. His background in theoretical physics informs a rigorous, data-driven approach to model design and problem solving. Known for combining deep acoustic expertise with practical engineering, he bridges research and scalable product delivery in conversational AI. Colleagues rely on him for both technical mentorship and strategic direction in building robust ASR platforms.
11 years of coding experience
14 years of employment as a software developer
MSc theoretical physics, MSc theoretical physics at V. N. Karazin Kharkiv National University
English, Russian, Ukrainian, German
Github Skills (41)
python10
data-science10
spell10
machine-learning10
ml10
deep-learning10
tensorflow10
deep-neural-networks10
neural-network10
architecture7
semantics7
image-recognition6
sentence5
speech-to-text5
parser5
Programming languages (3)
Github contributions (5)
sciforce/phones-las
Jan 2019 - Apr 2020
Articulatory features estimation using Listen Attend and Spell architecture.
Contributions:108 commits, 21 PRs, 45 pushes in 1 year 2 months
spelllisten-attend-and-spellestimationattendarchitecture
sciforce/listen-attend-and-spell
Jan 2019 - Jan 2019
Tensorflow implementation of "Listen, Attend and Spell" architecture with additional experimental features.
Contributions:7 PRs, 35 pushes, 9 branches in 12 days
experimental-featuresdeep-learningspelladditionallisten-attend-and-spell
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.