DDSP-QbE++: Improving Speech Quality for Speech Anonymisation for Atypical Speech

• URL: http://arxiv.org/abs/2604.09246v1
• Date: Fri, 10 Apr 2026 11:58:58 GMT
• Title: DDSP-QbE++: Improving Speech Quality for Speech Anonymisation for Atypical Speech
• Abstract summary: We propose improvements to the excitation stage of the subtractive synthesisP-QbE training pipeline for voice conversion.<n>We incorporate explicit voicing detection to gate the harmonic excitation, suppressing the periodic component in unvoiced regions and replacing it with filtered noise.<n>The proposed approach is lightweight, differentiable, and integrates seamlessly into the existingP-QbE training pipeline with no additional learnable parameters.
• Score: 4.129225533930966
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 introduce aliasing artefacts that manifest perceptually as buzziness and spectral distortion, particularly at higher fundamental frequencies. We propose two targeted improvements to the excitation stage of the DDSP-QbE subtractive synthesizer. First, we incorporate explicit voicing detection to gate the harmonic excitation, suppressing the periodic component in unvoiced regions and replacing it with filtered noise, thereby avoiding aliased harmonic content where it is most perceptually disruptive. Second, we apply Polynomial Band-Limited Step (PolyBLEP) correction to the phase-accumulated oscillator, substituting the hard waveform discontinuity at each phase wrap with a smooth polynomial residual that cancels alias-generating components without oversampling or spectral truncation. Together, these modifications yield a cleaner harmonic roll-off, reduced high-frequency artefacts, and improved perceptual naturalness, as measured by MOS. The proposed approach is lightweight, differentiable, and integrates seamlessly into the existing DDSP-QbE training pipeline with no additional learnable parameters.

Related papers

• Fractional-Order Adaptive Motion Magnification: Phase-Reliability Weighting for Noise-Constrained Video Amplification [51.56484100374058]
  We propose Fractional-order Adaptive Motion Magnification, a pipeline developed first offline and then as a causal stream.<n>It replaces the constant temporal gain with a Grnwald--Letnikov derivative of fractional order, giving continuous control over high-frequency emphasis.<n>Real videos show improved spatial selectivity and lower background noise in every case.
  arXiv  Detail & Related papers  (2026-09-03T21:43:22Z)
• Spectral Gating via Damped Oscillations for Adaptive Implicit Neural Representations [24.706105488382818]
  Implicit Neural Representations (INRs) have been proven successful in encoding continuous signals through coordinate-based networks.<n>They face a spectral dilemma: periodic activations capture fine details but act as all-pass filters that memorise noise, while spatially compact activations regularise effectively but suffer from low-frequency bias.<n>We propose to model each neuron's activation as the steady-state response of a sinusoidally-forced damped harmonic oscillator.
  arXiv  Detail & Related papers  (2026-06-22T11:59:47Z)
• Dive into Waves: Morlet Spectral Transformer for Cross-Subject Emotion Decoding from EEG [5.886986014593717]
  Cross-subject emotion recognition is a practically important yet challenging problem in brain-computer modeling.<n>Existing approaches rely on large pretrained foundation models, which require massive data yet still struggle with cross-subject variability.<n>We propose the Morlet Spectral Transformer (MST), built around three interfaces and integrated with a EEG-related Transformer backbone.
  arXiv  Detail & Related papers  (2026-05-30T20:38:34Z)
• Prosody-Guided Harmonic Attention for Phase-Coherent Neural Vocoding in the Complex Spectrum [1.3066182802188198]
  We introduce prosody-guided harmonic attention to enhance voiced segment encoding and directly predict complex spectral components for waveform synthesis via inverse STFT.<n>Experiments on benchmark datasets demonstrate consistent gains over HiFi-GAN and AutoVocoder: F0 RMSE reduced by 22 percent, voiced/unvoiced error lowered by 18 percent, and MOS scores improved by 0.15.<n>These results show that prosody-guided attention combined with direct complex spectrum modeling yields more natural, pitch-accurate, and robust synthetic speech, setting a strong foundation for expressive neural vocoding.
  arXiv  Detail & Related papers  (2026-01-20T20:53:24Z)
• Non-contact Vital Signs Detection in Dynamic Environments [0.61915796293339]
  We propose a novel DC offset calibration method alongside a Hilbert and Differential Cross-Multiply (HADCM) demodulation algorithm.<n>The approach estimates time-varying DC offsets from neighboring signal peaks and valleys, then employs both differential forms and Hilbert transforms of the I/Q channel signals to extract vital sign information.
  arXiv  Detail & Related papers  (2025-05-13T09:11:48Z)
• PAD: Phase-Amplitude Decoupling Fusion for Multi-Modal Land Cover Classification [49.37555541088792]
  Phase-Amplitude Decoupling (PAD) is a frequency-aware framework that separates phase (modality-shared) and amplitude (modality-complementary) components.<n>This work establishes a new paradigm for physics-aware multi-modal fusion in remote sensing.
  arXiv  Detail & Related papers  (2025-04-27T07:21:42Z)
• Joint Transmit and Pinching Beamforming for Pinching Antenna Systems (PASS): Optimization-Based or Learning-Based? [89.05848771674773]
  A novel antenna system ()-enabled downlink multi-user multiple-input single-output (MISO) framework is proposed.<n>It consists of multiple waveguides, which equip numerous low-cost antennas, named (PAs)<n>The positions of PAs can be reconfigured to both spanning large-scale path and space.
  arXiv  Detail & Related papers  (2025-02-12T18:54:10Z)
• UDHF2-Net: Uncertainty-diffusion-model-based High-Frequency TransFormer Network for Remotely Sensed Imagery Interpretation [17.289252835606533]
  Uncertainty-diffusion-model-based high-Frequency TransFormer network (UDHF2-Net) is the first to be proposed.<n> UDHF2-Net is a spatially-stationary-and-non-stationary high-frequency connection paradigm (SHCP)<n>Mask-and-geo-knowledge-based uncertainty diffusion module (MUDM) is a self-supervised learning strategy.<n>A frequency-wise semi-pseudo-Siamese UDHF2-Net is the first to be proposed to balance accuracy and complexity for change detection.
  arXiv  Detail & Related papers  (2024-06-23T15:03:35Z)
• DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection [80.20339155618612]
  DiffusionAD is a novel anomaly detection pipeline comprising a reconstruction sub-network and a segmentation sub-network.<n>A rapid one-step denoising paradigm achieves hundreds of times acceleration while preserving comparable reconstruction quality.<n>Considering the diversity in the manifestation of anomalies, we propose a norm-guided paradigm to integrate the benefits of multiple noise scales.
  arXiv  Detail & Related papers  (2023-03-15T16:14:06Z)
• Digital noise spectroscopy with a quantum sensor [57.53000001488777]
  We introduce and experimentally demonstrate a quantum sensing protocol to sample and reconstruct the auto-correlation of a noise process. Walsh noise spectroscopy method exploits simple sequences of spin-flip pulses to generate a complete basis of digital filters. We experimentally reconstruct the auto-correlation function of the effective magnetic field produced by the nuclear-spin bath on the electronic spin of a single nitrogen-vacancy center in diamond.
  arXiv  Detail & Related papers  (2022-12-19T02:19:35Z)
• Temporal-Spatial Neural Filter: Direction Informed End-to-End Multi-channel Target Speech Separation [66.46123655365113]
  Target speech separation refers to extracting the target speaker's speech from mixed signals. Two main challenges are the complex acoustic environment and the real-time processing requirement. We propose a temporal-spatial neural filter, which directly estimates the target speech waveform from multi-speaker mixture.
  arXiv  Detail & Related papers  (2020-01-02T11:12:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.