Jian Wu
Research Scientist at ByteDance
Bellevue, Washington, United States
Summary
🤩
Rockstar🎓
Top SchoolJian Wu is a research scientist based in Bellevue with nine years focused on speech technologies, spanning recognition, enhancement, separation, and generation. He has progressed from internships at Alibaba, Tencent, and Microsoft research labs to applied scientist roles and now leads speech generation and understanding research at ByteDance. His work balances foundational signal-processing approaches and modern LLM-driven speech pipelines, with practical impact in multi-talker ASR, diarization, speaker-change detection, and robust multi-channel separation. Jian’s career shows a pattern of solving real-world conversational-audio challenges at scale, and he brings deep cross-company experience integrating audio-visual and multilingual methods into production-oriented systems.
8 years of coding experience
3 years of employment as a software developer
Master's degree, Computer Science and Technology, Master's degree, Computer Science and Technology at Northwestern Polytechnical University
Github Skills (56)
speech-to-text10
mls10
speech-processing10
aps10
speaker-verification10
whisper10
speech-enhancement10
speech-synthesis10
automatic-speech-recognition10
morse-code10
location10
kaldi10
masking10
speech10
mfcc10
Programming languages (4)
Github contributions (5)
funcwj/deep-clustering
Jun 2018 - Dec 2019
deep clustering method for single-channel speech separation
Contributions:9 commits, 2 PRs, 5 pushes in 1 year 5 months
pytorchdeep-learningmethodsingle-channelgmm
funcwj/voice-filter
Apr 2019 - Nov 2020
A unofficial Pytorch implementation of Google's VoiceFilter
Contributions:8 commits, 1 PR, 1 push in 1 year 7 months
pytorchspeech-separationpytorch-implementation
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.