Dynamic Pitch Warping for Expressive Vocal Retuning

Daniel Hernan Molina Villota; Christophe D'Alessandro; Olivier Perrotin
DAFx-2023 - Copenhagen
This work introduces the use of the Dynamic Pitch Warping (DPW) method for automatic pitch correction of singing voice audio signals. DPW is designed to dynamically tune any pitch trajectory to a predefined scale while preserving its expressive ornamentation. DPW has three degrees of freedom to modify the fundamental frequency (f0 ) signal: detection interval, critical time, and transition time. Together, these parameters allow us to define a pitch velocity condition that triggers an adaptive correction of the pitch trajectory (pitch warping). We compared our approach to Antares Autotune (the most commonly used software brand, abbreviated as ATA in this article). The pitch correction in ATA has two degrees of freedom: a triggering threshold (flextune) and the transition time (retune speed). The pitch trajectories that we compare were extracted from autotuned-in-ATA audio signals, and the DPW algorithm implemented over the f0 of the input audio tracks. We studied specifically pitch correction for three typical situations of f0 curves: staircase, vibrato, free-path. We measured the proximity of the corrected pitch trajectories to the original ones for each case obtaining that the DPW pitch correction method is better to preserve vibrato while keeping the f0 free path. In contrast, ATA is more effective in generating staircase curves, but fails for notsmall vibratos and free-path curves. We have also implemented an off-line automatic picth tuner using DPW.