mlsanityData to 14 Oct 2026

Self-Attention for Audio Super-Resolution

arXiv 2108.11637 ↗First posted 26 Aug 2021cs.SD cs.LG eess.AScited by 9

Not on the map. Why?

Abstract (arXiv)

Convolutions operate only locally, thus failing to model global interactions. Self-attention is, however, able to learn representations that capture long-range dependencies in sequences. We propose a network architecture for audio super-resolution that combines convolution and self-attention. Attention-based Feature-Wise Linear Modulation (AFiLM) uses self-attention mechanism instead of recurrent neural networks to modulate the activations of the convolutional model. Extensive experiments show that our model outperforms existing approaches on standard benchmarks. Moreover, it allows for more parallelization resulting in significantly faster training.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 18 of its 43 references that are in the map. First posted on arXiv 26 Aug 2021.

Builds on

18 of 43 references.

References · 18

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2016Layer Normalizationcited by 5,669
  5. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  6. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,333
  7. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,863
  8. 2016WaveNet: A Generative Model for Raw Audiocited by 1,722
  9. 2016Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Networkcited by 1,204
  10. 2016Neural Combinatorial Optimization with Reinforcement Learningcited by 608
  11. 2019Attention Augmented Convolutional Networkscited by 363
  12. 2018Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separationcited by 125
6 more
  1. 2016SampleRNN: An Unconditional End-to-End Neural Audio Generation Modelcited by 110
  2. 2019Temporal FiLM: Capturing Long-Range Sequence Dependencies with Feature-Wise Modulationscited by 36
  3. 2020Speech Enhancement using Self-Adaptation and Multi-Head Self-Attentioncited by 28
  4. 2018Improved Speech Enhancement with the Wave-U-Netcited by 23
  5. 2020NU-GAN: High resolution neural upsampling with GANcited by 11
  6. 2020Phase-aware music super-resolution using generative adversarial networkscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 2; 2024: 2; 2025: 2; 2026: 2.

9 papers.

  1. 2023AudioSR: Versatile Audio Super-resolution at Scalecited by 39
  2. 2022CMGAN: Conformer-Based Metric-GAN for Monaural Speech Enhancementcited by 23
  3. 2024TRAMBA: A Hybrid Transformer and Mamba Architecture for Practical Audio and Bone Conduction Speech Super Resolution and Enhancement on Mobile and Wearable Platformscited by 11
  4. 2023mdctGAN: Taming transformer-based GAN for speech super-resolution with Modified DCT spectracited by 6
  5. 2025EDNet: A Versatile Speech Enhancement Framework with Gating Mamba Mechanism and Phase Shift-Invariant Trainingcited by 3
  6. 2026LatentFlowSR: High-Fidelity Audio Super-Resolution via Noise-Robust Latent Flow Matchingcited by 1
  7. 2024Speech Bandwidth Expansion Via High Fidelity Generative Adversarial Networkscited by 0
  8. 2025SUBARU: A Practical Approach to Power Saving in Hearables Using SUB-Nyquist Audio Resolution Upsamplingcited by 0
  9. 2026P2Flow: Phoneme-aware Progressive Flow Matching for Extreme Speech Super-Resolutioncited by 0