Summary
Rudolf Braun is a research engineer with 11 years of experience building and improving speech recognition systems across startups, research labs, and cloud services. Currently on AWS Transcribe Science, he brings deep hands-on expertise in ASR model training, OOV-word recognition, subword modeling, and self-supervised learning from prior roles at Idiap and Speechmatics. He has founded and led audio-focused ventures—including a navigation device for the blind and an on-device free speech-to-text app—demonstrating a mix of product intuition and applied research. Rudolf has published peer-reviewed work on OOV recognition and has practical experience adapting WFSTs and automatic pronunciation learning for multilingual ASR. Comfortable moving models from research to production, he has consulted for telecom clients and scaled systems across dozens of languages. Based in New York, he pairs startup grit with academic rigor to solve real-world speech problems.
11 years of coding experience
5 years of employment as a software developer
Bachelor of Engineering (B.Eng.) Engineering Physics, Bachelor of Engineering (B.Eng.) Engineering Physics at Carl von Ossietzky University of Oldenburg