Ivan Yakovlev
Research Engineer at Kaggle
Barcelona, Catalonia, Spain
Summary
👤
Senior🎓
Top SchoolIvan Yakovlev is a Research Engineer based in Barcelona with nine years of experience building ML/DL systems, focused for the last six+ years on speech and voice AI including ASR and ASV. He has driven production-ready speaker verification solutions, created one of the largest weakly supervised speaker verification datasets, and contributed to state-of-the-art voice activity detection and embedding-conversion techniques. His work at ID R&D yielded academic papers and competition wins (VoxSRC, SASV), and he has productionized models on diverse hardware including TPUs. A Kaggle Competitions Master and former AR/VR software engineer, he blends rigorous research with practical deployment skills and an unusual background in quantum mechanics.
9 years of coding experience
8 years of employment as a software developer
Бакалавр технических наук, Квантовая Механика, Бакалавр технических наук, Квантовая Механика at Санкт-Петербургский Государственный Университет
Русский, Английский
Github Skills (93)
transformers10
language-model10
python10
text-to-speech10
deep-learning10
speech10
transformer10
nlp10
speech-synthesis10
tensorflow10
natural-language-processing10
pytorch10
machine-learning10
bert10
speech-recognition10
Programming languages (6)
Github contributions (5)
IDRnD/redimnet
Jul 2024 - Mar 2025
The official pytorch implemention of the Intespeech 2024 paper "Reshape Dimensions Network for Speaker Recognition"
Contributions:1 PR, 13 pushes, 43 comments in 8 months
vanIvan/ctc-segmentation
Jul 2022 - Dec 2023
Segment an audio file and obtain utterance alignments. (Python package)
Contributions:1 push in 1 year 5 months
pythonaudio-filealignmentsutteranceaudio
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.