Yu Zhang
Focusing on Multi-Modal Generative AI (Speech/Spatial Audio/Singing Voice).
This profile was put together from Yu's public GitHub portfolio, and they haven't joined Vibetown yet, so reach them through their portfolio. Is this you? Contact us to update or remove it.
About
Yu Zhang works in AI engineering and ML & data science, based in Hangzhou, Zhejiang (bytedance). Focusing on Multi-Modal Generative AI (Speech/Spatial Audio/Singing Voice). Public projects on GitHub include StyleSinger (PyTorch Implementation of StyleSinger(AAAI 2024): Style Transfer for Out-of-Domain Singing Voice Synthesis), TCSinger (PyTorch Implementation of TCSinger(EMNLP 2024): Zero-Shot Singing Voice Synthesis with Style Transfer and…) and ISDrama (Dataset and evaluation code of ISDrama(ACM-MM 2025): Immersive Spatial Drama Generation through Multimodal…), mostly written in Python, C++ and TypeScript.
Projects 6
StyleSinger
PyTorch Implementation of StyleSinger(AAAI 2024): Style Transfer for Out-of-Domain Singing Voice Synthesis
github.comTCSinger
PyTorch Implementation of TCSinger(EMNLP 2024): Zero-Shot Singing Voice Synthesis with Style Transfer and Multi-Level Style Control
github.comISDrama
Dataset and evaluation code of ISDrama(ACM-MM 2025): Immersive Spatial Drama Generation through Multimodal Prompting
github.com- github.com
VersBand
PyTorch Implementation of VersBand(EMNLP 2025): Versatile Framework for Song Generation with Prompt-based Control
- github.com
TCSinger2
PyTorch Implementation of TCSinger 2(ACL 2025): Customizable Multilingual Zero-shot Singing Voice Synthesis
Xiaoheihe Cli
小黑盒游戏记录、个人评分与短评、社区内容操作 CLI，支持 SDK、REST 和 MCP
github.com