Summary
Seunghyun Lee is a language modeling engineer with 10 years of experience building robust ASR and AI systems that amplify human connection and inclusion. Currently at Cerence AI, he drives the transition from traditional AM+LM pipelines to end-to-end Transformer-based ASR for automotive applications, optimizing latency, robustness, and domain adaptation for both cloud and embedded platforms. His background includes research on Transformer and Wav2Vec2.0 interpretability at UIUC and hands-on experience deploying multi-n-gram LM compositions, weighted data-clustering strategies, and targeted error-reduction methods to lower WER in real-world environments. Comfortable communicating across engineering and product teams, he pairs deep signal-processing and engineering training with practical production experience. An educator at heart, he has taught and mentored hundreds of students in circuits and computing, bringing a pragmatic, explainability-focused perspective to applied speech research.
10 years of coding experience
1 year of employment as a software developer
Korean Minjok Leadership Academy (KMLA)
Master of Science - MS Electrical and Computer Engineering, Master of Science - MS Electrical and Computer Engineering at University of Illinois Urbana-Champaign
English, Korean, Chinese, Spanish