Xinjian Li
PhD Candidate
Summary
👤
SeniorXinjian Li is a research scientist at Google DeepMind with a decade of experience focused on machine learning for speech and audio, currently improving audio capabilities for Gemini models. He holds a Ph.D. from CMU LTI and has blended industry research and engineering at Google Brain and Microsoft, where he worked on East Asian input method editors. His work spans the full research-to-product lifecycle, from doctoral-level modeling to deploying robust systems in large-scale platforms. Comfortable switching between deep research and pragmatic engineering, he brings both theoretical rigor and production-grade implementation skills. Based in the United States, he maintains an active professional presence (xinjianl.com) that reflects his interdisciplinary training across CMU and the University of Tokyo. A not-obvious strength is his cross-cultural expertise in language technologies, informed by extensive academic and engineering work across Japan and the U.S.
10 years of coding experience
Github Skills (21)
speaker-diarization10
machine-translation10
pytorch10
speech-processing10
chainer10
speech-enhancement10
text-to-speech10
voice-conversion10
speech-synthesis10
grapheme10
kaldi10
tokenizer10
speech10
phonetics10
deep-learning9
Programming languages (4)
Github contributions (5)
xinjli/transphone
Jan 2022 - Jan 2023
phoneme tokenizer and grapheme-to-phoneme model for 8k languages
Contributions:25 commits, 8 PRs, 35 pushes in 1 year
graphemetokenizerg2pphoneme-conversionphonetics
xinjli/kaldi-cmake
Apr 2019 - Apr 2020
create CMakeLists.txt for kaldi
Contributions:9 commits, 1 PR, 7 pushes in 1 year
kaldi
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.