StylePitcher: Generating Style-Following and Expressive Pitch Curves for Versatile Singing Tasks

Jingyue Huang, Qihui Yang, Fei-Yueh Chen, Julian McAuley, Randal Leistikow, Yongyi Zang

Keywords: F0 Estimation, Singing Voice Synthesis and Conversion, Pitch Correction, Rectified Flow Matching

TL;DR: We propose StylePitcher, a general-purpose pitch curve generator that learns singer style from reference audio while preserving alignment with the intended melody.

Abstract: Existing pitch curve generators face two main challenges: they often neglect singer-specific expressiveness, reducing their ability to capture individual singing styles. And they are typically developed as auxiliary modules for specific tasks such as pitch correction, singing voice synthesis, or voice conversion, which restricts their generalization capability. We propose StylePitcher, a general-purpose pitch curve generator that learns singer style from reference audio while preserving alignment with the intended melody. Built upon a rectified flow matching architecture, StylePitcher flexibly incorporates symbolic music scores and pitch context as conditions for generation, and can seamlessly adapt to diverse singing tasks without retraining. Objective and subjective evaluations across various singing tasks demonstrate that StylePitcher improves style similarity and audio quality while maintaining pitch accuracy comparable to task-specific baselines.

Track: Paper Track

Confirmation: Paper Track: I confirm that I have followed the formatting guideline and anonymized my submission.

Submission Number: 68