mlsanityData to 7 Oct 2026

PeriodGrad: Towards Pitch-Controllable Neural Vocoder Based on a Diffusion Probabilistic Model

arXiv 2402.14692 ↗First posted 22 Feb 2024eess.AS cs.LG cs.SDcited by 3

On the map: Diffusion models → Audio, speech and music

Abstract (arXiv)

This paper presents a neural vocoder based on a denoising diffusion probabilistic model (DDPM) incorporating explicit periodic signals as auxiliary conditioning signals. Recently, DDPM-based neural vocoders have gained prominence as non-autoregressive models that can generate high-quality waveforms. The neural vocoders based on DDPM have the advantage of training with a simple time-domain loss. In practical applications, such as singing voice synthesis, there is a demand for neural vocoders to generate high-fidelity speech waveforms with flexible pitch control. However, conventional DDPM-based neural vocoders struggle to generate speech waveforms under such conditions. Our proposed model aims to accurately capture the periodic structure of speech waveforms by incorporating explicit periodic signals. Experimental results show that our model improves sound quality and provides better pitch control than conventional DDPM-based neural vocoders.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in Audio, speech and music, one of 14 directions in Diffusion models. Builds on 26 of its 32 references that are in the map. First posted on arXiv 22 Feb 2024.

Builds on

26 of 32 references.

Closest ancestors · 5

Same direction, newest first

  1. 2022Hierarchical Diffusion Models for Singing Voice Neural Vocoder14 Oct
  2. 2022SpecGrad: Diffusion Probabilistic Model based Neural Vocoder with Adaptive Noise Spectral Shaping31 Mar
  3. 2022InferGrad: Improving Diffusion Models for Vocoder by Considering Inference in Training8 Feb
  4. 2021PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Dependent Adaptive Prior11 Jun
  5. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesis21 Sep

Other references · 21

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  5. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  6. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  7. 2021Variational Diffusion Modelscited by 1,145
  8. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,139
  9. 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 800
  10. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 620
  11. 2019MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesiscited by 351
  12. 2019Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogramcited by 337
9 more
  1. 2018WaveGlow: A Flow-based Generative Network for Speech Synthesiscited by 308
  2. 2018Efficient Neural Audio Synthesiscited by 218
  3. 2017Parallel WaveNet: Fast High-Fidelity Speech Synthesiscited by 214
  4. 2016SampleRNN: An Unconditional End-to-End Neural Audio Generation Modelcited by 110
  5. 2018LPCNet: Improving Neural Speech Synthesis Through Linear Predictioncited by 109
  6. 2019WaveFlow: A Compact Flow-based Model for Raw Audiocited by 51
  7. 2020HiFiSinger: Towards High-Fidelity Neural Singing Voice Synthesiscited by 39
  8. 2021Sinsy: A Deep Neural Network-Based Singing Voice Synthesis Systemcited by 14
  9. 2022Source-Filter HiFi-GAN: Fast and Pitch Controllable High-Fidelity Neural Vocodercited by 11

Built on by

Cited by year

Citing papers per year: 2025: 3.

3 papers.

  1. 2025PitchFlower: A flow-based neural audio codec with pitch controllabilitycited by 1
  2. 2025GLA-Grad++: An Improved Griffin-Lim Guided Diffusion Model for Speech Synthesiscited by 0
  3. 2025Pseudo-Cepstrum: Pitch Modification for Mel-Based Neural Vocoderscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023DiffAR: Denoising Diffusion Autoregressive Model for Raw Speech Waveform Generation
  2. 2022WaveFit: An Iterative and Non-autoregressive Neural Vocoder based on Fixed-Point Iteration
  3. 2024Speaking in Wavelet Domain: A Simple and Efficient Approach to Speed up Speech Diffusion Model
  4. 2022BDDM: Bilateral Denoising Diffusion Models for Fast and High-Quality Speech Synthesis
  5. 2025WaveFM: A High-Fidelity and Efficient Vocoder Based on Flow Matching
  6. 2023HiddenSinger: High-Quality Singing Voice Synthesis via Neural Audio Codec and Latent Diffusion Models
  7. 2023CoMoSpeech: One-Step Speech and Singing Voice Synthesis via Consistency Model
  8. 2021Restoring degraded speech via a modified diffusion model