Jinglin Liu is a quantitative researcher with eight years of experience applying machine learning to speech, music, and NLP problems, currently working in Hangzhou at 幻方AI after research roles at ByteDance and Alibaba DAMO Academy. With an MS from Zhejiang University, Jinglin blends academic depth and production-focused engineering—evidenced by substantive contributions to the widely cited DiffSinger singing-voice synthesis project, where they added pipelines, MIDI support, and practical checkpoints. Comfortable moving models from research into usable workflows, they have a track record of improving codebases and documentation while collaborating across industry research teams. Colleagues know them for tackling audio-centric ML challenges that sit at the intersection of signal processing and generative modeling.
9 years of coding experience
Master of Science - MS, Computer Science, Master of Science - MS, Computer Science at 浙江大学
DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism (SVS & TTS); AAAI 2022; Official code
Role in this project:
ML Engineer
Contributions:1 release, 37 commits, 1 PR in 8 months
Contributions summary:Jinglin contributed significantly to the DiffSinger project, focused on singing voice synthesis. Their work involved adding new singing pipelines, particularly for the OpenCPOP dataset, and integrating MIDI support. They also modified and updated existing code, including file adjustments and improvements, demonstrating active involvement in core functionality and workflow enhancements. Additionally, the user provided checkpoints and made updates to the README, reflecting a combination of development and project documentation.
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.