mlsanityData to 7 Oct 2026

SpecGrad: Diffusion Probabilistic Model based Neural Vocoder with Adaptive Noise Spectral Shaping

arXiv 2203.16749 ↗First posted 31 Mar 2022eess.AS cs.LG cs.SDcited by 37

On the map: Diffusion models → Audio, speech and music

Abstract (arXiv)

Neural vocoder using denoising diffusion probabilistic model (DDPM) has been improved by adaptation of the diffusion noise distribution to given acoustic features. In this study, we propose SpecGrad that adapts the diffusion noise so that its time-varying spectral envelope becomes close to the conditioning log-mel spectrogram. This adaptation by time-varying filtering improves the sound quality especially in the high-frequency bands. It is processed in the time-frequency domain to keep the computational cost almost the same as the conventional DDPM-based neural vocoders. Experimental results showed that SpecGrad generates higher-fidelity speech waveform than conventional DDPM-based neural vocoders in both analysis-synthesis and speech enhancement scenarios. Audio demos are available at wavegrad.github.io/specgrad/.

Key facts. Cited by 37 papers in the map (data through 7 Oct 2026). Placed in Audio, speech and music, one of 14 directions in Diffusion models. Builds on 28 of its 39 references that are in the map. First posted on arXiv 31 Mar 2022.

Builds on

28 of 39 references.

Closest ancestors · 5

Same direction, newest first

  1. 2022BDDM: Bilateral Denoising Diffusion Models for Fast and High-Quality Speech Synthesis25 Mar
  2. 2022InferGrad: Improving Diffusion Models for Vocoder by Considering Inference in Training8 Feb
  3. 2021PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Dependent Adaptive Prior11 Jun
  4. 2021Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech13 May
  5. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesis21 Sep

Other references · 23

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  3. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,139
  4. 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 800
  5. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 620
  6. 2019MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesiscited by 351
  7. 2019Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogramcited by 337
  8. 2018WaveGlow: A Flow-based Generative Network for Speech Synthesiscited by 308
  9. 2018Adversarial Audio Synthesiscited by 222
  10. 2018Efficient Neural Audio Synthesiscited by 218
  11. 2022It's Raw! Audio Generation with State-Space Modelscited by 171
  12. 2016SampleRNN: An Unconditional End-to-End Neural Audio Generation Modelcited by 110
11 more
  1. 2020Multi-band MelGAN: Faster Waveform Generation for High-Quality Text-to-Speechcited by 63
  2. 2019WaveFlow: A Compact Flow-based Model for Raw Audiocited by 51
  3. 2021VoiceFixer: Toward General Speech Restoration with Neural Vocodercited by 50
  4. 2019Neural source-filter waveform models for statistical parametric speech synthesiscited by 46
  5. 2020A Spectral Energy Distance for Parallel Speech Synthesiscited by 42
  6. 2020HiFi-GAN: High-Fidelity Denoising and Dereverberation Based on Speech Deep Features in Adversarial Networkscited by 40
  7. 2020A Curated Dataset of Urban Scenes for Audio-Visual Scene Analysiscited by 16
  8. 2021DF-Conformer: Integrated architecture of Conv-TasNet and Conformer using linear complexity self-attention for speech enhancementcited by 16
  9. 2021WARP-Q: Quality Prediction For Generative Neural Speech Codecscited by 12
  10. 2019Parametric Resynthesis with neural vocoderscited by 8
  11. 2019Speaker independence of neural vocoders and their effect on parametric resynthesis speech enhancementcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 9; 2023: 10; 2024: 12; 2025: 5; 2026: 1.

37 papers.

Sort:

By area:

  1. 2022A Survey on Generative Diffusion Modelcited by 238
  2. 2022Speech Enhancement and Dereverberation with Diffusion-based Generative Modelscited by 195
  3. 2023StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Modelscited by 148
  4. 2022HouseDiffusion: Vector Floorplan Generation via a Diffusion Model with Discrete and Continuous Denoisingcited by 72
  5. 2023A Survey on Audio Diffusion Models: Text To Speech Synthesis and Enhancement in Generative AIcited by 68
  6. 2023StyleDiffusion: Prompt-Embedding Inversion for Text-Based Editingcited by 68
  7. 2023Generative Pre-training for Speech with Flow Matchingcited by 55
  8. 2022Diffusion-based Generative Speech Source Separationcited by 41
  9. 2023Imaginary Voice: Face-styled Diffusion Model for Text-to-Speechcited by 27
  10. 2023Miipher: A Robust Speech Restoration Model Integrating Self-Supervised Speech and Text Representationscited by 22
  11. 2022ResGrad: Residual Denoising Diffusion Probabilistic Models for Text to Speechcited by 21
  12. 2022WaveFit: An Iterative and Non-autoregressive Neural Vocoder based on Fixed-Point Iterationcited by 20
25 more
  1. 2024Detecting Out-Of-Distribution Earth Observation Images with Diffusion Modelscited by 14
  2. 2024PeriodWave: Multi-Period Flow Matching for High-Fidelity Waveform Generationcited by 12
  3. 2024FreGrad: Lightweight and Fast Frequency-aware Diffusion Vocodercited by 11
  4. 2022Hierarchical Diffusion Models for Singing Voice Neural Vocodercited by 10
  5. 2023DiffSketching: Sketch Control Image Synthesis with Diffusion Modelscited by 10
  6. 2023HierVST: Hierarchical Adaptive Zero-shot Voice Style Transfercited by 9
  7. 2024RFWave: Multi-band Rectified Flow for Audio Waveform Reconstructioncited by 9
  8. 2025Source Separation by Flow Matchingcited by 8
  9. 2025WaveFM: A High-Fidelity and Efficient Vocoder Based on Flow Matchingcited by 7
  10. 2023BigVSAN: Enhancing GAN-based Neural Vocoders with Slicing Adversarial Networkcited by 6
  11. 2024GLA-Grad: A Griffin-Lim Extended Waveform Generation Diffusion Modelcited by 6
  12. 2022Robust One-Shot Singing Voice Conversioncited by 5
  13. 2025UniWav: Towards Unified Pre-training for Speech Representation Learning and Generationcited by 5
  14. 2024Accelerating High-Fidelity Waveform Generation via Adversarial Flow Matching Optimizationcited by 4
  15. 2024SF-Speech: Straightened Flow for Zero-Shot Voice Clonecited by 4
  16. 2024SpecDiff-GAN: A Spectrally-Shaped Noise Diffusion GAN for Speech and Music Synthesiscited by 3
  17. 2024PeriodGrad: Towards Pitch-Controllable Neural Vocoder Based on a Diffusion Probabilistic Modelcited by 3
  18. 2024Facial Expression-Enhanced TTS: Combining Face Representation and Emotion Intensity for Adaptive Speechcited by 2
  19. 2022Framewise WaveGAN: High Speed Adversarial Vocoder in Time Domain with Very Low Computational Complexitycited by 1
  20. 2023FastFit: Towards Real-Time Iterative Neural Vocoder by Replacing U-Net Encoder With Multiple STFTscited by 1
  21. 2024DPI-TTS: Directional Patch Interaction for Fast-Converging and Style Temporal Modeling in Text-to-Speechcited by 1
  22. 2024Zero-Shot Mono-to-Binaural Speech Synthesiscited by 0
  23. 2025RestoreGrad: Signal Restoration Using Conditional Denoising Diffusion Models with Jointly Learned Priorcited by 0
  24. 2025GLA-Grad++: An Improved Griffin-Lim Guided Diffusion Model for Speech Synthesiscited by 0
  25. 2026WaveNeXt 2: ConvNeXt-Based Fast Neural Vocoders With Residual Denoising and Sub-Modeling for GAN and Diffusion Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025LatentVoiceGrad: Nonparallel Voice Conversion with Latent Diffusion/Flow-Matching Models
  2. 2021Restoring degraded speech via a modified diffusion model
  3. 2024Speaking in Wavelet Domain: A Simple and Efficient Approach to Speed up Speech Diffusion Model
  4. 2023DiffAR: Denoising Diffusion Autoregressive Model for Raw Speech Waveform Generation
  5. 2025BridgeVoC: Revitalizing Neural Vocoder from a Restoration Perspective
  6. 2025Enhancing Spectrogram Realism in Singing Voice Synthesis via Explicit Bandwidth Extension Prior to Vocoder ↗
  7. 2021NU-Wave: A Diffusion Probabilistic Model for Neural Audio Upsampling
  8. 2025WaveLLDM: Design and Development of a Lightweight Latent Diffusion Model for Speech Enhancement and Restoration