Taishi Nakashima
Assistant Professor at Tokyo Metropolitan University
Tokyo, Japan
Summary
👤
Senior🎓
Top SchoolTaishi Nakashima is an Assistant Professor at Tokyo Metropolitan University specializing in real-time blind source separation and acoustic signal processing, with eight years of research experience bridging theory and low-latency practical systems. He has produced top-recognized work (ICASSP 2023 Top 3% paper) on fast online AuxIVA methods—introducing iterative source steering and matrix-inversion-free algorithms that prioritize tracking moving speakers and reducing computational cost. Skilled in Python, C++, and MATLAB, he focuses on real-time audio I/O, optimization, and open-source implementations that enable adaptive separation for dynamic microphone setups. His background includes a competitive JSPS fellowship and industry collaboration at LINE Corp where his dereverberation and BSS work reached ICASSP, reflecting a consistent thread of translating academic advances into deployable audio solutions.
8 years of coding experience
学士（工学）, Department of Engineering Science, 学士（工学）, Department of Engineering Science at Osaka UniversityAssociate of Engineering, 電子情報コース, Associate of Engineering, 電子情報コース at Osaka Prefecture University College of TechnologyPh.D. in Computer Science, Computer Science, 4.0/4.0, Ph.D. in Computer Science, Computer Science, 4.0/4.0 at Tokyo Metropolitan University
English, Japanese, Korean
Github Skills (22)
acoustics9
signal-processing9
audio9
realms9
giphy8
audio-effect8
signal8
digital-signal-processing8
mls8
scenarios7
probot7
prototyping7
music7
pitch6
runner6
Programming languages (5)
Github contributions (5)
onolab-tmu/asp-tutorial-2022
Jun 2022 - Jul 2022
Ono laboratory audio signal processing exercise for beginners.
Contributions:41 reviews, 82 commits, 42 PRs in 28 days
signallaboratoryfor-beginnersaudioaudio-signal-processing
onolab-tmu/morise-asa
May 2021 - Jul 2021
ひたすら楽して音響信号解析の勉強会
Contributions:33 reviews, 33 PRs, 37 pushes in 1 month
github-botgiphyprobotrealmsrunner
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.