New AI Model Enhances Singing Voice Conversion with Independent Style Control

Researchers have developed VibE-SVC2, an advanced singing voice conversion framework designed to enhance control over singing styles. This new model offers independent control over pitch and timbre, addressing limitations in previous versions. For pitch, it introduces an Energy Style Converter to manage pitch-energy entanglement and a Zero-shot Pitch Style Converter for mimicking reference audio. To improve timbre conversion, especially for challenging styles like vocal fry, a Subharmonic Correction algorithm refines the F0 contour. Evaluations show VibE-SVC2 surpasses existing methods in fine-grained style control. AI

RANK_REASON The cluster contains an academic paper detailing a new model and methodology for singing voice conversion. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• Energy Style Converter
• Subharmonic Correction
• VibE-SVC
• VibE-SVC2
• Zero-shot Pitch Style Converter

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →