Summary
Hieu-thi Luong is a Singapore-based Speech Scientist with 11 years of experience bridging academic research and applied product work in speech and language processing. She has advanced expertise in ASR, generative AI, multimodal systems, and practical defenses against speech deepfakes, now applying that knowledge at Fortemedia on deepfake detection and speech enhancement. Her postdoctoral work produced a patent-worthy TTS/VC hybrid that clones voices from under five minutes of audio and methods that synthesize realistic room acoustics to harden detectors. At NTU she led creation of a 130-hour content-driven fake-speech dataset and a tool that accelerated data generation tenfold, demonstrating both research depth and productivity improvements. She combines signal-processing rigor with machine-learning innovation across low-resource and multilingual settings, having bootstrapped Vietnamese and Japanese speech systems. Outside work she describes herself as a "full-time dreamer" — a hint at a creative, sleep-deprived approach to problem solving.
11 years of coding experience
8 years of employment as a software developer
Doctor of Philosophy - PhD Multidisciplinary Science - Informatics, Doctor of Philosophy - PhD Multidisciplinary Science - Informatics at The Graduate University for Advanced Studies, SOKENDAI
Master of Science (M.Sc.) Computer Science, Master of Science (M.Sc.) Computer Science at VNUHCM - University of Science
Vietnamese, English, Japanese