Shan Yang
Summary
👤
SeniorShan Yang is a Staff Applied Scientist with eight years of experience building production-grade ML systems across speech synthesis, multimodal video understanding, and 3D reconstruction. After a Ph.D. in Computer Science from UNC Chapel Hill, Shan drove research-to-product work at Google and Amazon before joining Adobe Foundry, bridging cutting-edge research with scalable engineering. His background spans inverse problems in graphics to monocular video 3D reconstruction and recent focus on speech synthesis, reflecting a rare combo of geometric vision and audio modeling expertise. Based in Mountain View, he is comfortable moving systems from research prototypes into robust, deployable services and often brings insights from academic research to solve practical product challenges.
8 years of coding experience
Github Skills (14)
speech-synthesis10
pre-trained-model10
python9
tensorflow9
machine-learning9
vocoder8
mnist7
codec7
audio6
generative-model6
paper6
text-to-speech5
pytorch5
deep-learning4
Programming languages (3)
Github contributions (5)
syang1993/syang1993.github.io
Feb 2018 - Apr 2021
Contributions:49 commits, 84 pushes, 1 branch in 3 years 1 month
syang1993/gst-tacotron
Mar 2018 - Dec 2018
A tensorflow implementation of the "Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis"
Contributions:46 commits, 3 PRs, 32 pushes in 8 months
speech-synthesistensorflowexpressive-tacotronexpressive-speech-synthesistacotron
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.