Media Interaction Group | メディアインタラクション研究グループ
Human Informatics and Interaction Research Institute | 人間情報インタラクション研究部門
National Institute of Advanced Industrial Science and Technology (AIST) | 國立研究開發法人 産業技術総合研究所
Office: Central 2, 1-1-1 Umezono, Tsukuba, Ibaraki, 305-8568 Japan | 〒305-8568 茨城県つくば市梅園１−１−１中央第二
edward.lin [at] aist.go.jp or edward_lin [at] alumni.sutd.edu.sg
Curriculum Vitae (CV) | 履歴書 | 職務経歴書
Researchmap, Google Scholar, ORCiD, publons, ResearchGate, dblp (computer science bibliography)
Kin Wah Edward, LIN (林 堅華) is an AIST Postdoctoral Researcher (産総研特別研究員), working at the Media Interaction Group (メディアインタラクション研究グループ), National Institute of Advanced Industrial Science and Technology (AIST, 國立研究開發法人 産業技術総合研究所), Japan. He received his Ph.D. degree in Information Systems Technology and Design from Singapore University of Technology and Design (SUTD) in 2018. Edward has 10 years research experience to invent and implement the cutting-edge techniques (e.g., mathematical optimization, human-computer interaction, and machine learning) for developing the potential commercial applications. For example, he did stochastic modelling for the fairness data traffic in Wi-Fi Mesh network; he developed mobile apps with latest hardware capacity (e.g., the facial recognition camera equipped on the mobile device) to improve singing skill and facial expression; he used machine learning techniques to visualize singing style and used deep learning techniques to (1) separate the singing voice and the background music, and (2) do the singing voice conversion. The process analysis, research findings and results are summarized in 14 top peer-reviewed conferences and journals papers, which have attracted many citations. In addition, he serves as a reviewer for many top conference and journal papers, including The 21st International Society for Music Information Retrieval Conference (ISMIR).
Edward also has years of multi-national studying and working experience. It allows him to adapt different working nature or environments, ranging from the teamwork-oriented start-up company in Hong Kong to the largest public research institution in Japan, where he works as an independent researcher.
My researches focus on automatically analyzing and synthesizing singing voice, especially in popular music, via the approaches of machine learning and human computer interaction. Research topics include (1) Singing Voice Conversion and Generation, (2) Singers Support iOS app, (3) Singing Voice Separation, (4) Sinusoidal Partial Tracking for Singing Analysis, (5) Audio Feature Optimization and (6) Singing Style Visualization under Musical Events.
IEEE/ACM Transactions on Audio, Speech and Language Processing, 2020
Computational Intelligence and Neuroscience, 2020
IEEE Access, 2020-2019
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2021
The 21st International Society for Music Information Retrieval Conference (ISMIR), 2020
Prof. Simon Lui|雷兆恆 教授,
nomislui [at] gmail.com
Tencent Music Entertainment (TME) | 騰訊音樂
Singapore University of Technology and Design | 新加坡科技設計大學
Caritas Institute of Higher Education | 明愛專上學院