Work Experience: Co-founded AudAI, contributed to the development of singing voice synthesis, voice conversion, and neural vocoder. Position: PhD Researcher.
Education
Degree: PhD Student; Institution: KAIST (Korea Advanced Institute of Science and Technology); Advisor: Professor Juhan Nam; Time: Current; Specialization: Music and Audio Computing Lab (MAC Lab).
Background
Research Interests: Improving the quality, efficiency, and controllability of generative models for audio generation and processing. Professional Field: Music and Audio Computing. Brief Introduction: Passionate about developing audio generative models that achieve high perceptual quality in real-world scenarios. Worked on tasks such as video-to-audio generation, audio super-resolution, and acoustic transfer.
Miscellany
Personal Interests: Music production, can find his music through YouTube.