Po-chun Hsu
Software Engineer at Realtek Semiconductor Corp.
New Taipei, Taiwan
Summary
👤
Senior🎓
Top SchoolPo-chun Hsu is a software engineer and Ph.D. researcher from National Taiwan University specializing in low-latency, high-quality speech synthesis, including TTS, voice conversion, and neural vocoders. With eight years of experience spanning academia and industry, he has interned at Taiwan AILabs, collaborated with Meta on SSL-enhanced TTS that reduced required speech data by 90% while preserving ASR performance, and recently joined Realtek Semiconductor. His work blends deep learning research and practical engineering, delivering efficient, robust Mandarin TTS systems and improved vocoders. Trained in electrical engineering and communication engineering, he brings a strong theoretical foundation paired with hands-on model optimization and deployment experience. Based in New Taipei, he is adept at translating cutting-edge research into production-ready speech technologies. An understated strength is his focus on latency-aware design, making his systems suitable for real-time applications.
8 years of coding experience
Doctor of Philosophy - PhD, Graduate Institute of Communication Engineering, Doctor of Philosophy - PhD, Graduate Institute of Communication Engineering at National Taiwan University
English, Chinese
Github Skills (9)
pytorch5
inference4
generative4
realtime4
speech3
synthesis3
speech-recognition2
speech-synthesis2
darknet1
Programming languages (3)
Github contributions (5)
BogiHsu/Tacotron2-PyTorch
Jun 2019 - Apr 2022
Contributions:2 releases, 92 commits, 71 pushes in 2 years 10 months
faliwang/Universal-Adaptor
Jul 2021 - Jul 2022
Contributions:43 commits, 2 pushes in 11 months
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.