mlsanityData to 14 Oct 2026

Pseudo-Cepstrum: Pitch Modification for Mel-Based Neural Vocoders

arXiv 2512.16519 ↗First posted 18 Dec 2025cs.SD cs.LG eess.AScited by 0

Not on the map. Why?

Abstract (arXiv)

This paper introduces a cepstrum-based pitch modification method that can be applied to any mel-spectrogram representation. As a result, this method is compatible with any mel-based vocoder without requiring any additional training or changes to the model. This is achieved by directly modifying the cepstrum feature space in order to shift the harmonic structure to the desired target. The spectrogram magnitude is computed via the pseudo-inverse mel transform, then converted to the cepstrum by applying DCT. In this domain, the cepstral peak is shifted without having to estimate its position and the modified mel is recomputed by applying IDCT and mel-filterbank. These pitch-shifted mel-spectrogram features can be converted to speech with any compatible vocoder. The proposed method is validated experimentally with objective and subjective metrics on various state-of-the-art neural vocoders as well as in comparison with traditional pitch modification methods.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 22 of its 37 references that are in the map. First posted on arXiv 18 Dec 2025.

Builds on

22 of 37 references.

References · 22

  1. 2016WaveNet: A Generative Model for Raw Audiocited by 1,722
  2. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,354
  3. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,154
  4. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 622
  5. 2021Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speechcited by 561
  6. 2018WaveGlow: A Flow-based Generative Network for Speech Synthesiscited by 309
  7. 2022BigVGAN: A Universal Neural Vocoder with Large-Scale Trainingcited by 251
  8. 2018Efficient Neural Audio Synthesiscited by 219
  9. 2023Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesiscited by 153
  10. 2020FastPitch: Parallel Text-to-speech with Pitch Predictioncited by 151
  11. 2018LPCNet: Improving Neural Speech Synthesis Through Linear Predictioncited by 110
  12. 2019Neural source-filter waveform models for statistical parametric speech synthesiscited by 46
10 more
  1. 2020Controllable Neural Prosody Synthesiscited by 10
  2. 2020Quasi-Periodic Parallel WaveGAN: A Non-autoregressive Raw Waveform Generative Model with Pitch-dependent Dilated Convolution Neural Networkcited by 8
  3. 2025WaveFM: A High-Fidelity and Efficient Vocoder Based on Flow Matchingcited by 7
  4. 2024FreeV: Free Lunch For Vocoders Through Pseudo Inversed Mel Filtercited by 6
  5. 2024Fine-Grained and Interpretable Neural Speech Editingcited by 6
  6. 2021Neural Pitch-Shifting and Time-Stretching with Controllable LPCNetcited by 4
  7. 2021KaraTuner: Towards end to end natural pitch correction for singing voice in karaokecited by 4
  8. 2022Controllable speech synthesis by learning discrete phoneme-level prosodic representationscited by 3
  9. 2024PeriodGrad: Towards Pitch-Controllable Neural Vocoder Based on a Diffusion Probabilistic Modelcited by 3
  10. 2025Neurodyne: Neural Pitch Manipulation with Representation Learning and Cycle-Consistency GANcited by 2

Built on by

Not cited yet.