MagiaSVS: Singing Voice Synthesis with Lyrics and Pitch Guidance via a Unified-Modal Large Language Model

Hao Zhou 0033, Zhiyue Wu, Xingjian Du, Haining Zhang, Binhui Wang. MagiaSVS: Singing Voice Synthesis with Lyrics and Pitch Guidance via a Unified-Modal Large Language Model. In Companion of the 2025 ACM International Joint Conference on Pervasive and Ubiquitous Computing, UbiComp Companion 2025, Espoo, Finland, October 12-16, 2025. pages 656-661, ACM, 2025. [doi]

Abstract

Abstract is missing.