mlsanityData to 7 Oct 2026

HyperSound: Generating Implicit Neural Representations of Audio Signals with Hypernetworks

arXiv 2211.01839 ↗First posted 3 Nov 2022cs.SD cs.AI cs.LGcited by 12

Not on the map. Why?

Abstract (arXiv)

Implicit neural representations (INRs) are a rapidly growing research field, which provides alternative ways to represent multimedia signals. Recent applications of INRs include image super-resolution, compression of high-dimensional signals, or 3D rendering. However, these solutions usually focus on visual data, and adapting them to the audio domain is not trivial. Moreover, it requires a separately trained model for every data sample. To address this limitation, we propose HyperSound, a meta-learning method leveraging hypernetworks to produce INRs for audio signals unseen at training time. We show that our approach can reconstruct sound waves with quality comparable to other state-of-the-art models.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 20 of its 25 references that are in the map. First posted on arXiv 3 Nov 2022.

Builds on

20 of 25 references.

References · 20

  1. 2015Fast R-CNNcited by 2,930
  2. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  3. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  4. 2015Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)cited by 1,061
  5. 2016HyperNetworkscited by 1,003
  6. 2021SoundStream: An End-to-End Neural Audio Codeccited by 756
  7. 2019MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesiscited by 351
  8. 2019Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogramcited by 337
  9. 2019Continual learning with hypernetworkscited by 267
  10. 2017Neural Audio Synthesis of Musical Notes with WaveNet Autoencoderscited by 222
  11. 2017Parallel WaveNet: Fast High-Fidelity Speech Synthesiscited by 214
  12. 2021Modulated Periodic Activations for Generalizable Local Functional Representationscited by 140
8 more
  1. 2017TasNet: time-domain audio separation network for real-time, single-channel speech separationcited by 115
  2. 2016SampleRNN: An Unconditional End-to-End Neural Audio Generation Modelcited by 110
  3. 2021RAVE: A variational autoencoder for fast and high-quality neural audio synthesiscited by 72
  4. 2019Hypernetwork functional image representationcited by 65
  5. 2021CDPAM: Contrastive learning for perceptual audio similaritycited by 42
  6. 2022Neural Vocoder is All You Need for Speech Super-resolutioncited by 37
  7. 2018SING: Symbol-to-Instrument Neural Generatorcited by 23
  8. 2020Hypernetwork approach to generating point cloudscited by 20

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 3; 2025: 3; 2026: 2.

12 papers.

  1. 2023A Brief Review of Hypernetworks in Deep Learningcited by 102
  2. 2024Boosting Neural Representations for Videos with a Conditional Decodercited by 29
  3. 2023Blended-NeRF: Zero-Shot Object Generation and Blending in Existing Neural Radiance Fieldscited by 23
  4. 2023Focus Your Attention (with Adaptive IIR Filters)cited by 12
  5. 2023Siamese SIREN: Audio Compression with Implicit Neural Representationscited by 11
  6. 2025Spectral Bottleneck in Sinusoidal Representation Networks: Noise is All You Needcited by 2
  7. 2024Extreme Compression of Adaptive Neural Imagescited by 1
  8. 2025QFGN: A Quantum Approach to High-Fidelity Implicit Neural Representationscited by 1
  9. 2025mmWEAVER: Environment-Specific mmWave Signal Synthesis from a Photo and Activity Descriptioncited by 1
  10. 2026Implicit Neural Representations: A Signal Processing Perspectivecited by 1
  11. 2024D'OH: Decoder-Only Random Hypernetworks for Implicit Neural Representationscited by 0
  12. 2026UniqueSplat: View-conditioned 3D Gaussian Splatting for Generalizable 3D Reconstructioncited by 0