Wen Hsiao
Research Scientist at ByteDance
San Jose, California, United States
Summary
🤩
Rockstar🎓
Top SchoolWen Hsiao is a research scientist based in San Jose with nine years of experience specializing in audio, music, computer vision, and digital signal processing. Currently at ByteDance, he focuses on music transcription and understanding, building on prior research and engineering roles at Taiwan AILabs and Academia Sinica. He has strong hands-on ML expertise—evidenced by significant contributions to the MuseGAN music-generation codebase where he implemented core GAN components, temporal modeling, and loss functions. Wen combines academic rigor from National Tsing Hua University with practical production skills, bridging research prototypes to deployable systems. He has navigated both industry and visa-driven entrepreneurial steps, showing persistence and an ability to operate independently as well as in collaborative research teams.
9 years of coding experience
6 years of employment as a software developer
Master's degree Computer Science, Master's degree Computer Science at National Tsing Hua University
Github Skills (6)
music-generation10
machine-learning10
tensorflow10
python10
generative-adversarial-network10
backend7
Programming languages (4)
Github contributions (5)
salu133445/musegan
Jan 2018 - Aug 2018
An AI for Music Generation
Role in this project:
ML Engineer
ML EngineerContributions:26 commits, 26 pushes, 8 comments in 7 months
Contributions summary:Wen contributed significantly to the core codebase of an AI for Music Generation project, primarily focusing on the development and refinement of machine learning models. The commits involve the definition of various model components, including encoders, generators, and discriminators, with specific attention to the implementation of the Nowbar and Temporal models. The code changes also reveal the implementation of loss functions, gradient penalties, and other critical elements of the GAN architecture used for music generation.
music-generationdeep-learninggenerative-adversarial-networkmachine-learninggan
wayne391/2018_Deep_Learning_HW-GAN
Nov 2017 - Mar 2019
Contributions:25 commits, 24 pushes, 1 branch in 1 year 4 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.