mlsanityData to 7 Oct 2026

Neural Vocoder is All You Need for Speech Super-resolution

arXiv 2203.14941 ↗First posted 28 Mar 2022eess.AS cs.AI cs.LGcited by 37

Not on the map. Why?

Abstract (arXiv)

Speech super-resolution (SR) is a task to increase speech sampling rate by generating high-frequency components. Existing speech SR methods are trained in constrained experimental settings, such as a fixed upsampling ratio. These strong constraints can potentially lead to poor generalization ability in mismatched real-world cases. In this paper, we propose a neural vocoder based speech super-resolution method (NVSR) that can handle a variety of input resolution and upsampling ratios. NVSR consists of a mel-bandwidth extension module, a neural vocoder module, and a post-processing module. Our proposed system achieves state-of-the-art results on the VCTK multi-speaker benchmark. On 44.1 kHz target resolution, NVSR outperforms WSRGlow and Nu-wave by 8% and 37% respectively on log spectral distance and achieves a significantly better perceptual quality. We also demonstrate that prior knowledge in the pre-trained vocoder is crucial for speech SR by performing mel-bandwidth extension with a simple replication-padding method. Samples can be found in https://haoheliu.github.io/nvsr.

Key facts. Cited by 37 papers in the map (data through 7 Oct 2026). Builds on 15 of its 27 references that are in the map. First posted on arXiv 28 Mar 2022.

Builds on

15 of 27 references.

References · 15

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  3. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,139
  4. 2021NU-Wave: A Diffusion Probabilistic Model for Neural Audio Upsamplingcited by 50
  5. 2021VoiceFixer: Toward General Speech Restoration with Neural Vocodercited by 50
  6. 2021Decoupling Magnitude and Phase Estimation with Deep ResUNet for Music Source Separationcited by 48
  7. 2017Audio Super Resolution using Neural Networkscited by 26
  8. 2021Conditional Sound Generation Using Neural Discrete Time-Frequency Representation Learningcited by 24
  9. 2021WSRGlow: A Glow-based Waveform Generative Model for Audio Super-Resolutioncited by 19
  10. 2020NU-GAN: High resolution neural upsampling with GANcited by 11
  11. 2020TFGAN: Time and Frequency Domain Based Generative Adversarial Network for High-fidelity Speech Synthesiscited by 11
  12. 2021Learning Continuous Representation of Audio for Arbitrary Scale Super Resolutioncited by 9
3 more
  1. 2021CWS-PResUNet: Music Source Separation with Channel-wise Subband Phase-aware ResUNetcited by 9
  2. 2020Phase-aware music super-resolution using generative adversarial networkscited by 5
  3. 2019Speech bandwidth extension with WaveNetcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 6; 2023: 6; 2024: 4; 2025: 16; 2026: 5.

37 papers.

Sort:

By area:

  1. 2023AudioLDM: Text-to-Audio Generation with Latent Diffusion Modelscited by 592
  2. 2023AudioSR: Versatile Audio Super-resolution at Scalecited by 39
  3. 2022Analysing Diffusion-based Generative Approaches versus Discriminative Approaches for Speech Restorationcited by 34
  4. 2022CMGAN: Conformer-Based Metric-GAN for Monaural Speech Enhancementcited by 22
  5. 2022ResGrad: Residual Denoising Diffusion Probabilistic Models for Text to Speechcited by 21
  6. 2023Blind Audio Bandwidth Extension: A Diffusion-Based Zero-Shot Approachcited by 21
  7. 2022Conditioning and Sampling in Variational Diffusion Models for Speech Super-Resolutioncited by 20
  8. 2025FLowHigh: Towards Efficient and High-Quality Audio Super-Resolution with Single-Step Flow Matchingcited by 18
  9. 2025Audio Super-Resolution with Latent Bridge Modelscited by 13
  10. 2022HyperSound: Generating Implicit Neural Representations of Audio Signals with Hypernetworkscited by 12
  11. 2023Hypernetworks build Implicit Neural Representations of Soundscited by 11
  12. 2025A2SB: Audio-to-Audio Schrodinger Bridgescited by 11
25 more
  1. 2023Leveraging Pre-trained AudioLDM for Sound Generation: A Benchmark Studycited by 10
  2. 2024Wave-U-Mamba: An End-To-End Framework For High-Quality And Efficient Speech Super Resolutioncited by 9
  3. 2023mdctGAN: Taming transformer-based GAN for speech super-resolution with Modified DCT spectracited by 6
  4. 2025FlashSR: One-step Versatile Audio Super-resolution via Diffusion Distillationcited by 5
  5. 2025UniFlow-Audio: Unified Flow Matching for Audio Generation from Omni-Modalitiescited by 5
  6. 2024Vector Quantized Diffusion Model Based Speech Bandwidth Extensioncited by 4
  7. 2025A Composite Predictive-Generative Approach to Monaural Universal Speech Enhancementcited by 4
  8. 2025Real-Time Streamable Generative Speech Restoration with Flow Matchingcited by 4
  9. 2025EDNet: A Versatile Speech Enhancement Framework with Gating Mamba Mechanism and Phase Shift-Invariant Trainingcited by 3
  10. 2025Inference-time Scaling for Diffusion-based Audio Super-resolutioncited by 3
  11. 2025UniverSR: Unified and Versatile Audio Super-Resolution via Vocoder-Free Flow Matchingcited by 3
  12. 2022Nonparallel High-Quality Audio Super Resolution with Domain Adaptation and Resampling CycleGANscited by 2
  13. 2025Generative Adversarial Network based Voice Conversion: Techniques, Challenges, and Recent Advancementscited by 2
  14. 2025Universal Semantic Disentangled Privacy-preserving Speech Representation Learningcited by 1
  15. 2025A High-Fidelity Speech Super Resolution Network using a Complex Global Attention Module with Spectro-Temporal Losscited by 1
  16. 2026LatentFlowSR: High-Fidelity Audio Super-Resolution via Noise-Robust Latent Flow Matchingcited by 1
  17. 2024Effects of Dataset Sampling Rate for Noise Cancellation through Deep Learningcited by 0
  18. 2024Speech Bandwidth Expansion Via High Fidelity Generative Adversarial Networkscited by 0
  19. 2025SUBARU: A Practical Approach to Power Saving in Hearables Using SUB-Nyquist Audio Resolution Upsamplingcited by 0
  20. 2025CIS-BWE: Chaos-Informed Speech Bandwidth Extensioncited by 0
  21. 2025CogSR: Semantic-Aware Speech Super-Resolution via Chain-of-Thought Guided Flow Matchingcited by 0
  22. 2026FastWave: Optimized Diffusion Model for Audio Super-Resolutioncited by 0
  23. 2026Fast and Flexible Audio Bandwidth Extension via Vocoscited by 0
  24. 2026Stage-adaptive audio diffusion modelingcited by 0
  25. 2026VeRe-Flow: Guiding Flow Matching toward Clean Speech via Velocity Contrastive Regularization and Representation Alignment for Noise-Robust Bandwidth Expansioncited by 0