mlsanityData to 14 Oct 2026

Hypernetworks build Implicit Neural Representations of Sounds

arXiv 2302.04959 ↗First posted 9 Feb 2023cs.LG cs.AI cs.SDcited by 11

Not on the map. Why?

Abstract (arXiv)

Implicit Neural Representations (INRs) are nowadays used to represent multimedia signals across various real-life applications, including image super-resolution, image compression, or 3D rendering. Existing methods that leverage INRs are predominantly focused on visual data, as their application to other modalities, such as audio, is nontrivial due to the inductive biases present in architectural attributes of image-based INR models. To address this limitation, we introduce HyperSound, the first meta-learning approach to produce INRs for audio samples that leverages hypernetworks to generalize beyond samples observed in training. Our approach reconstructs audio samples with quality comparable to other state-of-the-art models and provides a viable alternative to contemporary sound representations used in deep neural networks for audio processing, such as spectrograms.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 32 of its 41 references that are in the map. First posted on arXiv 9 Feb 2023.

Builds on

32 of 41 references.

References · 32

  1. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
  2. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
  3. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,238
  4. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  5. 2016WaveNet: A Generative Model for Raw Audiocited by 1,722
  6. 2018On the Spectral Bias of Neural Networkscited by 1,341
  7. 2015Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)cited by 1,070
  8. 2016HyperNetworkscited by 1,027
  9. 2021SoundStream: An End-to-End Neural Audio Codeccited by 771
  10. 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
  11. 2019MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesiscited by 354
  12. 2019Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogramcited by 340
20 more
  1. 2019Continual learning with hypernetworkscited by 273
  2. 2017Neural Audio Synthesis of Musical Notes with WaveNet Autoencoderscited by 225
  3. 2017Parallel WaveNet: Fast High-Fidelity Speech Synthesiscited by 215
  4. 2020MetaSDF: Meta-learning Signed Distance Functionscited by 214
  5. 2022DiffRF: Rendering-Guided 3D Radiance Field Diffusioncited by 204
  6. 2021Implicit Neural Representations for Image Compressioncited by 162
  7. 2021Modulated Periodic Activations for Generalizable Local Functional Representationscited by 140
  8. 2017TasNet: time-domain audio separation network for real-time, single-channel speech separationcited by 115
  9. 2016SampleRNN: An Unconditional End-to-End Neural Audio Generation Modelcited by 110
  10. 2019Deep Learning for Audio Signal Processingcited by 92
  11. 2022Transformers as Meta-Learners for Implicit Neural Representationscited by 79
  12. 2021RAVE: A variational autoencoder for fast and high-quality neural audio synthesiscited by 73
  13. 2019Hypernetwork functional image representationcited by 65
  14. 2021Seeing Implicit Neural Representations as Fourier Seriescited by 50
  15. 2021CDPAM: Contrastive learning for perceptual audio similaritycited by 42
  16. 2022Neural Vocoder is All You Need for Speech Super-resolutioncited by 37
  17. 2022HyperTime: Implicit Neural Representation for Time Seriescited by 24
  18. 2018SING: Symbol-to-Instrument Neural Generatorcited by 23
  19. 2020Hypernetwork approach to generating point cloudscited by 20
  20. 2021Towards Lightweight Controllable Audio Synthesis with Conditional Implicit Neural Representationscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 4; 2025: 5; 2026: 1.

11 papers.

  1. 2024VeGaS: Video Gaussian Splattingcited by 9
  2. 2024EVOS: Efficient Implicit Neural Training via EVOlutionary Selectorcited by 7
  3. 2023HyperMask: Adaptive Hypernetwork-based Masks for Continual Learningcited by 4
  4. 2025Exploring Kernel Transformations for Implicit Neural Representationscited by 2
  5. 2025NTK-Guided Implicit Neural Teachingcited by 2
  6. 2024Rethinking Non-Negative Matrix Factorization with Implicit Neural Representationscited by 1
  7. 2025Boosting 3D Liver Shape Datasets with Diffusion Models and Implicit Neural Representationscited by 1
  8. 2024SegINR: Segment-wise Implicit Neural Representation for Sequence Alignment in Neural Text-to-Speechcited by 0
  9. 2025As Good as It KAN Get: High-Fidelity Audio Representationcited by 0
  10. 2025Beyond Heuristics: Globally Optimal Configuration of Implicit Neural Representationscited by 0
  11. 2026Atelier: Learning Local Self-Supervised Features for CryoEM Volumes via Hypernetworkscited by 0