Scholar
Shuqi Dai
Google Scholar ID: Sz788IIAAAAJ
PhD student, Carnegie Mellon University
Citations & Impact
Citations
558
H-index
10
i10-index
10
Publications
18
Co-authors
5
list available
Publications
Resume (English only)
Academic Achievements
- Involved in several projects like Everyone-Can-Sing (Zero-Shot Singing Voice Synthesis and Conversion), ExpressiveSinger (Multilingual and Multi-Style Score-based Singing Voice Synthesis), SingStyle111 (A Multilingual Singing Dataset With Style Transfer), Deep Music Generation via Music Frameworks, and Computational Study of Repetition and Structure in Popular Music. These projects cover singing voice synthesis, style transfer, multilingual support, etc.
Research Experience
- Interned at companies including Adobe, NVIDIA, Microsoft Research Asia, Google, and Hulu.
Education
- Ph.D. candidate at the Computer Science Department, Carnegie Mellon University, advised by Prof. Roger Dannenberg; received B.S. in Computer Science from Peking University, China, in July 2018.
Background
- Research interests lie in the innovative perspectives of music technology, aiming to transform how we listen to, understand, perform, and create music. Also explores the potential of music technology in benefiting individuals and society by integrating it with other areas such as health and education.
Miscellany
- Professional Pipa (Chinese traditional instrument) player with over 20 years of performance experience, tutored by Prof. Yabo Pan; received five years of formal Western music training at CMU School of Music with straight-A's; also composes and sings.
