Valentin Vielzeuf
Chercheur at Orange
Brittany, France
Summary
👤
Senior🎓
Top SchoolValentin Vielzeuf is a Senior Speech Research Scientist at Orange Rennes with 11 years of experience combining deep learning and signal processing to build E2E ASR and SLU systems and drive complexity reduction. He holds a PhD in Artificial Intelligence and a strong engineering background from École Centrale de Nantes, applying self-supervised training and spoken language modeling to real-world telecommunication problems. His career blends academic rigor—doctoral work on deep learning for multimodal and temporal data—with hands-on prototype development across industry and research settings. Based in Brittany, he has a track record of optimizing models for efficiency and has contributed to medical imaging reconstruction and gesture-initiated interaction projects earlier in his career, reflecting a wide-ranging curiosity beyond speech.
11 years of coding experience
Doctor of Philosophy - PhD, Artificial Intelligence, Doctor of Philosophy - PhD, Artificial Intelligence at Université de Caen NormandieMPSI et MP au Lycée Masséna, NiceMaster 2 (M2), Traitement du signal, Master 2 (M2), Traitement du signal at Ecole centrale de Nantes
French, English, German
Github Skills (33)
speech-to-text10
voice-recognition10
audio10
speaker-verification9
speech-processing9
audio-processing9
asr9
huggingface9
speech9
speech-recognition8
speech-synthesis8
speech-enhancement8
pytorch8
speaker-diarization8
transformers8
Programming languages (1)
Github contributions (5)
vielzeuf/The-Many-Variations-of-Emotion
Jan 2019 - Jul 2019
Contributions:35 commits, 10 pushes, 1 branch in 5 months
vielzeuf/speechbrain
Mar 2021 - Mar 2021
A PyTorch-based Speech Toolkit
Contributions:1 push, 1 branch in 1 day
pytorchspeech-toolkitspeech-recognitionspeech-synthesisspeech
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.