AI RESEARCH
DDSP-QbE++: Improving Speech Quality for Speech Anonymisation for Atypical Speech
arXiv CS.AI
•
ArXi:2604.09246v1 Announce Type: cross Differentiable Digital Signal Processing (DDSP) pipelines for voice conversion rely on subtractive synthesis, where a periodic excitation signal is shaped by a learned spectral envelope to reconstruct the target voice. In DDSP-QbE, the excitation is generated via phase accumulation, producing a sawtooth-like waveform whose abrupt discontinuities