Prompt-Singer: Controllable Singing-Voice-Synthesis with Natural Language Prompt

arXiv:2403.11780v1 Announce Type: cross
Abstract: Recent singing-voice-synthesis (SVS) methods have achieved remarkable audio quality and naturalness, yet they lack the capability to control the style attributes of the synthesized singing explicitly. We propose Prompt-Singer, the first SVS method that enables attribute controlling on singer gender, vocal range and volume with natural language. We adopt a model architecture based on a decoder-only transformer with a multi-scale hierarchy, and design a range-melody decoupled pitch representation that enables text-conditioned vocal range control while …

arxiv cs.ai cs.lg cs.sd eess.as language natural natural language natural language prompt prompt singer singing synthesis type voice