Summary
Teerapat Jenrungrot is a PhD student at the University of Washington and a Harvey Mudd graduate with a decade of experience at the intersection of audio, 3D/AR/VR, and computer vision. He has published and presented cutting-edge work—most notably an oral NeurIPS 2020 paper on deep learning speech separation—and built a neural speech codec (LMCodec) published at ICASSP 2023 that leverages large language models for ultra-low-rate compression. His internships at Google, Meta, Amazon, and Microsoft demonstrate a strong track record of moving research into production, from distributed training pipelines to deployed clustering algorithms. Equally comfortable with signal processing and deep learning, he combines rigorous academic methods with practical system engineering, including real-world voice separation and HRTF-based spatial audio prototypes. Based in Seattle, he focuses on bridging audio and visual modalities in immersive systems and often pursues unconventional cross-domain solutions that reuse language-model ideas for audio tasks.
10 years of coding experience
4 years of employment as a software developer
Doctor of Philosophy - PhD Computer Science, Doctor of Philosophy - PhD Computer Science at University of Washington
Bachelor of Science - BS Computer Science, Bachelor of Science - BS Computer Science at Harvey Mudd College
Thai, English, Japanese