Nelson Yalta
AI Engineer at Astemo Ltd.
Tokyo, Japan
Summary
🤩
Rockstar🎓
Top SchoolNelson Yalta is an AI Engineer based in Tokyo with a decade of experience applying deep learning to audio and robot audition problems, currently working at Astemo Ltd. He holds a Doctor of Engineering from Waseda University and has moved research into production roles at Hitachi and Hitachi Astemo, blending academic rigor with industrial deployment. Nelson contributes to prominent open-source projects such as espnet—improving build/docker reliability and CUDA detection—highlighting his strengths in back-end engineering and DevOps for speech processing toolkits. His background spans ASR, sound processing, and embedded robot audition, and he pairs low-level system fixes with model-driven research. A multilingual engineer with a foundation in electrical engineering, he brings pragmatic problem-solving from hotel IT support to large-scale AI infrastructure.
10 years of coding experience
6 years of employment as a software developer
Doctorado, Engineering, Doctorado, Engineering at 早稲田大学 WASEDA UniversityIngeniería, Electrical and Electronics Engineering, Ingeniería, Electrical and Electronics Engineering at Universidad Privada Antenor Orrego
Spanish, English, japones
Stackoverflow
11reputation
136reached
0answers
1question
Github Skills (12)
sh10
bash10
docker10
script10
shell10
dockers10
scripting10
linux8
pytorch8
cuda7
software-packaging6
visual-studio6
Programming languages (10)
Github contributions (5)
espnet/espnet
Jun 2018 - Jan 2023
End-to-End Speech Processing Toolkit
Role in this project:
Back-end Developer & DevOps Engineer
Back-end Developer & DevOps EngineerContributions:4 releases, 57 reviews, 395 commits in 4 years 8 months
Contributions summary:Nelson primarily focused on improving the efficiency of the existing codebase and making changes in the build/docker structure. The user was responsible for fixing errors in arguments used in the training script and improved the automatic detection of CUDA version and installation of software in the docker containers. The contributions involved updating the code, which improved the overall stability and maintainability of the software.
speech-recognitionspeech-separationchainerspoken-language-understandingspeech-processing
Fhrozen/pyimagesource
Oct 2018 - Feb 2020
Contributions:9 commits, 7 pushes, 1 branch in 1 year 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.