Yi-Chiao WU
Summary
👤
SeniorYi-chiao Wu is a research scientist with nine years of experience advancing neural audio technologies, currently at Meta Reality Labs in New York. Her work spans neural codecs, voice conversion, speech synthesis, and enhancement, contributing to high-profile projects such as Audiobox, MovieGen audio, and open-source releases like AudioDec and FlowDec. She holds a Ph.D. in Informatics from Nagoya University and has a strong track record in voice conversion challenges and dataset/tool releases (e.g., EARS), blending rigorous academic research with production-focused engineering. Notably, she has repeatedly improved robustness and efficiency in generative audio models—from WaveNet and WaveGlow optimizations to LPC-constraint techniques—demonstrating both innovation on benchmarks and practical impact in deployed systems.
10 years of coding experience
Github Skills (10)
preference10
codec9
baseline9
speech-synthesis9
pytorch8
audio8
speech8
voice-conversion7
music-generation5
vocoder2
Programming languages (2)
Github contributions (5)
bigpon/QPPWG
May 2020 - Oct 2022
Quasi-Periodic Parallel WaveGAN Pytorch implementation
Contributions:23 commits, 22 pushes, 1 branch in 2 years 5 months
pytorchspeech-synthesisneural-vocoderwavenetparallel-wavenet-vocoder
bigpon/QPNet
Nov 2019 - Mar 2021
Quasi-Periodic WaveNet Pytorch implementation
Contributions:16 commits, 15 pushes, 1 branch in 1 year 4 months
pytorchspeech-synthesiswavenetneural-vocoder
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.