mlsanityData to 7 Oct 2026

As Good as It KAN Get: High-Fidelity Audio Representation

arXiv 2503.02585 ↗First posted 4 Mar 2025cs.SD cs.CV eess.AScited by 0

Not on the map. Why?

Abstract (arXiv)

Implicit neural representations (INR) have gained prominence for efficiently encoding multimedia data, yet their applications in audio signals remain limited. This study introduces the Kolmogorov-Arnold Network (KAN), a novel architecture using learnable activation functions, as an effective INR model for audio representation. KAN demonstrates superior perceptual performance over previous INRs, achieving the lowest Log-SpectralDistance of 1.29 and the highest Perceptual Evaluation of Speech Quality of 3.57 for 1.5 s audio. To extend KAN's utility, we propose FewSound, a hypernetwork-based architecture that enhances INR parameter updates. FewSound outperforms the state-of-the-art HyperSound, with a 33.3% improvement in MSE and 60.87% in SI-SNR. These results show KAN as a robust and adaptable audio representation with the potential for scalability and integration into various hypernetwork frameworks. The source code can be accessed at https://github.com/gmum/fewsound.git.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 28 of its 50 references that are in the map. First posted on arXiv 4 Mar 2025.

Builds on

28 of 50 references.

References · 28

  1. 2017Attention Is All You Needcited by 59,932
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  3. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  4. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  5. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  6. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,301
  7. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  8. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  9. 2018On the Spectral Bias of Neural Networkscited by 1,321
  10. 2016HyperNetworkscited by 1,003
  11. 2021SoundStream: An End-to-End Neural Audio Codeccited by 756
  12. 2023Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Modelscited by 591
16 more
  1. 2019Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogramcited by 337
  2. 2020Learned Initializations for Optimizing Coordinate-Based Neural Representationscited by 240
  3. 2021Implicit Neural Representations for Image Compressioncited by 161
  4. 2022VideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time Super-Resolutioncited by 101
  5. 2019Hypernetwork functional image representationcited by 65
  6. 2021CDPAM: Contrastive learning for perceptual audio similaritycited by 42
  7. 2024SNAC: Multi-Scale Neural Audio Codeccited by 42
  8. 2023Improved DeepFake Detection Using Whisper Featurescited by 28
  9. 2022HyperMAML: Few-Shot Adaptation of Deep Models with Hypernetworkscited by 16
  10. 2024FreSh: Frequency Shifting for Accelerated Neural Representation Learningcited by 14
  11. 2023Hypernetworks build Implicit Neural Representations of Soundscited by 11
  12. 2023Siamese SIREN: Audio Compression with Implicit Neural Representationscited by 11
  13. 2023A Scalable Walsh-Hadamard Regularizer to Overcome the Low-degree Spectral Bias of Neural Networkscited by 10
  14. 2017Stochastic Maximum Likelihood Optimization via Hypernetworkscited by 7
  15. 2023Using joint training speaker encoder with consistency loss to achieve cross-lingual voice conversion and expressive voice conversioncited by 5
  16. 2024HyperPlanes: Hypernetwork Approach to Rapid NeRF Adaptationcited by 1

Built on by

Not cited yet.