4 papers · 1 filter
SaMoye: Zero-shot Singing Voice Conversion Model Based on Feature Disentanglement and Enhancement
Zihao Wang, Le Ma, Yongsheng Feng +3
Singing voice conversion (SVC) aims to convert a singer's voice to another singer's from a reference audio while keeping the original semantics. However, existing SVC methods can h…
MetaBGM: Dynamic Soundtrack Transformation For Continuous Multi-Scene Experiences With Ambient Awareness And Personalization
Haoxuan Liu, Zihao Wang, Haorong Hong +5
This paper introduces MetaBGM, a groundbreaking framework for generating background music that adapts to dynamic scenes and real-time user interactions. We define multi-scene as va…
MuDiT & MuSiT: Alignment with Colloquial Expression in Description-to-Song Generation
Zihao Wang, Haoxuan Liu, Jiaxing Yu +3
Amid the rising intersection of generative AI and human artistic processes, this study probes the critical yet less-explored terrain of alignment in human-centric automatic song co…
MuChin: A Chinese Colloquial Description Benchmark for Evaluating Language Models in the Field of Music
Zihao Wang, Shuyu Li, Tao Zhang +6
The rapidly evolving multimodal Large Language Models (LLMs) urgently require new benchmarks to uniformly evaluate their performance on understanding and textually describing music…