mlsanityData to 14 Oct 2026

Reconstruction of Sound Field through Diffusion Models

arXiv 2312.08821 ↗First posted 14 Dec 2023eess.AS cs.LG cs.SDcited by 8

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

Abstract (arXiv)

Reconstructing the sound field in a room is an important task for several applications, such as sound control and augmented (AR) or virtual reality (VR). In this paper, we propose a data-driven generative model for reconstructing the magnitude of acoustic fields in rooms with a focus on the modal frequency range. We introduce, for the first time, the use of a conditional Denoising Diffusion Probabilistic Model (DDPM) trained in order to reconstruct the sound field (SF-Diff) over an extended domain. The architecture is devised in order to be conditioned on a set of limited available measurements at different frequencies and generate the sound field in target, unknown, locations. The results show that SF-Diff is able to provide accurate reconstructions, outperforming a state-of-the-art baseline based on kernel interpolation.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Placed in Audio, speech and music, one of 14 directions in Diffusion models. Builds on 19 of its 41 references that are in the map. First posted on arXiv 14 Dec 2023.

Builds on

19 of 41 references.

Closest ancestors · 5

Same direction, newest first

  1. 2022Cold Diffusion for Speech Enhancement4 Nov
  2. 2022Conditioning and Sampling in Variational Diffusion Models for Speech Super-Resolution27 Oct
  3. 2022Solving Audio Inverse Problems with a Diffusion Model27 Oct
  4. 2022Hierarchical Diffusion Models for Singing Voice Neural Vocoder14 Oct
  5. 2022InferGrad: Improving Diffusion Models for Vocoder by Considering Inference in Training8 Feb

Other references · 14

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  5. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,238
  6. 2021Image Super-Resolution via Iterative Refinementcited by 1,511
  7. 2021Palette: Image-to-Image Diffusion Modelscited by 1,300
  8. 2017Deep Image Priorcited by 1,098
  9. 2019Machine learning in acoustics: theory and applicationscited by 36
  10. 2020Sound field reconstruction in rooms: inpainting meets super-resolutioncited by 10
  11. 2023Implicit neural representation with physics-informed neural networks for the reconstruction of the early part of room impulse responsescited by 8
  12. 2023Kernel interpolation of acoustic transfer functions with adaptive kernel for directed and residual reverberationscited by 4
2 more
  1. 2023Generative adversarial networks with physical sound field priorscited by 4
  2. 2022Physics-informed convolutional neural network with bicubic spline interpolation for sound field estimationcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 3; 2026: 2.

8 papers.

  1. 2024MambaFoley: Foley Sound Generation using Selective State-Space Modelscited by 3
  2. 2025DiffusionRIR: Room Impulse Response Interpolation using Diffusion Modelscited by 3
  3. 2024A Physics-Informed Neural Network-Based Approach for the Spatial Upsampling of Spherical Microphone Arrayscited by 2
  4. 2026RIR-Former: Coordinate-Guided Transformer for Continuous Reconstruction of Room Impulse Responsescited by 2
  5. 2024Blind Spatial Impulse Response Generation from Separate Room- and Scene-Specific Informationcited by 1
  6. 2025Towards HRTF Personalization using Denoising Diffusion Modelscited by 1
  7. 2025Gaussian Process Regression of Steering Vectors With Physics-Aware Deep Composite Kernels for Augmented Listeningcited by 0
  8. 2026SF-Flow: Sound field magnitude estimation via flow matching guided by sparse measurementscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesis
  2. 2022BinauralGrad: A Two-Stage Conditional Diffusion Probabilistic Model for Binaural Audio Synthesis
  3. 2026Few-shot Acoustic Synthesis with Multimodal Flow Matching
  4. 2024Diffusion Models for Audio Restoration
  5. 2023EDMSound: Spectrogram Based Diffusion Models for Efficient and High-Quality Audio Synthesis
  6. 2026DiffSOS: Acoustic Conditional Diffusion Model for Speed-of-Sound Reconstruction in Ultrasound Computed Tomography
  7. 2023From Discrete Tokens to High-Fidelity Audio Using Multi-Band Diffusion
  8. 2024Urban Sound Propagation: a Benchmark for 1-Step Generative Modeling of Complex Physical Systems