mlsanityData to 7 Oct 2026

Realistic Gramophone Noise Synthesis using a Diffusion Model

arXiv 2206.06259 ↗First posted 13 Jun 2022eess.AScited by 3

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

Abstract (arXiv)

This paper introduces a novel data-driven strategy for synthesizing gramophone noise audio textures. A diffusion probabilistic model is applied to generate highly realistic quasiperiodic noises. The proposed model is designed to generate samples of length equal to one disk revolution, but a method to generate plausible periodic variations between revolutions is also proposed. A guided approach is also applied as a conditioning method, where an audio signal generated with manually-tuned signal processing is refined via reverse diffusion to improve realism. The method has been evaluated in a subjective listening test, in which the participants were often unable to recognize the synthesized signals from the real ones. The synthetic noises produced with the best proposed unconditional method are statistically indistinguishable from real noise recordings. This work shows the potential of diffusion models for highly realistic audio synthesis tasks.

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 15 of its 23 references that are in the map. First posted on arXiv 13 Jun 2022.

Builds on

15 of 23 references.

Closest ancestors · 3

Same direction, newest first

  1. 2021CRASH: Raw Audio Score-based Generative Modeling for Controllable High-resolution Drum Sound Synthesis14 Jun
  2. 2021Symbolic Music Generation with Diffusion Models30 Mar
  3. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesis21 Sep

Other references · 12

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  4. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  5. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  6. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,286
  7. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  8. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,903
  9. 2021Variational Diffusion Modelscited by 1,145
  10. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 620
  11. 2022A Two-Stage U-Net for High-Fidelity Denoising of Historical Recordingscited by 17
  12. 2019Sound texture synthesis using convolutional neural networkscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 1; 2024: 0; 2025: 0; 2026: 1.

3 papers.

  1. 2022Solving Audio Inverse Problems with a Diffusion Modelcited by 62
  2. 2023Neural modeling of magnetic tape recorderscited by 3
  3. 2026Signal-Informed Temporal Routing for Vinyl Defect Regime Detectioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Discrete Diffusion Probabilistic Models for Symbolic Music Generation
  2. 2023Generating symbolic music using diffusion models
  3. 2023EDMSound: Spectrogram Based Diffusion Models for Efficient and High-Quality Audio Synthesis
  4. 2025Estimating Musical Surprisal from Audio in Autoregressive Diffusion Model Noise Spaces
  5. 2023From Discrete Tokens to High-Fidelity Audio Using Multi-Band Diffusion
  6. 2025Discrete-Time Diffusion-Like Models for Speech Synthesis
  7. 2023Controllable Music Production with Diffusion Models and Guidance Gradients
  8. 2022Conditional Diffusion Probabilistic Model for Speech Enhancement