Vibrato Expression Control for Singing Voice Conversion with Improving Independent Control

The article presents VibE-SVC2, an advanced singing voice conversion framework that enhances control over singing styles by introducing a novel Energy Style Converter and a Zero-shot Pitch Style Converter. The model allows independent control of vibrato extent through vibrato rate scaling and addresses challenges in converting specific phonation styles with a Subharmonic Correction algorithm. This framework significantly improves the expressiveness and quality of singing voice conversion, making it a valuable tool for practitioners in the field.