mlsanityData to 7 Oct 2026

Fre-GAN: Adversarial Frequency-consistent Audio Synthesis

arXiv 2106.02297 ↗First posted 4 Jun 2021eess.AS cs.LGcited by 24

Not on the map. Why?

Abstract (arXiv)

Although recent works on neural vocoder have improved the quality of synthesized audio, there still exists a gap between generated and ground-truth audio in frequency space. This difference leads to spectral artifacts such as hissing noise or reverberation, and thus degrades the sample quality. In this paper, we propose Fre-GAN which achieves frequency-consistent audio synthesis with highly improved generation quality. Specifically, we first present resolution-connected generator and resolution-wise discriminators, which help learn various scales of spectral distributions over multiple frequency bands. Additionally, to reproduce high-frequency components accurately, we leverage discrete wavelet transform in the discriminators. From our experiments, Fre-GAN achieves high-fidelity waveform generation with a gap of only 0.03 MOS compared to ground-truth audio while outperforming standard models in quality.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). Builds on 23 of its 33 references that are in the map. First posted on arXiv 4 Jun 2021.

Builds on

23 of 33 references.

References · 23

  1. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  2. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  3. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  4. 2017Improved Training of Wasserstein GANscited by 2,223
  5. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  6. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  7. 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,176
  8. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,139
  9. 2016Least Squares Generative Adversarial Networkscited by 1,000
  10. 2015Autoencoding beyond pixels using a learned similarity metriccited by 407
  11. 2019Making Convolutional Networks Shift-Invariant Againcited by 390
  12. 2019MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesiscited by 351
11 more
  1. 2019Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogramcited by 337
  2. 2018WaveGlow: A Flow-based Generative Network for Speech Synthesiscited by 308
  3. 2018Efficient Neural Audio Synthesiscited by 218
  4. 2019High Fidelity Speech Synthesis with Adversarial Networkscited by 90
  5. 2018FloWaveNet : A Generative Flow for Raw Audiocited by 54
  6. 2020SSD-GAN: Measuring the Realness in the Spatial and Spectral Domainscited by 38
  7. 2020Upsampling artifacts in neural audio synthesiscited by 28
  8. 2020Multi-SpectroGAN: High-Diversity and High-Fidelity Spectrogram Generation with Adversarial Style Combination for Speech Synthesiscited by 28
  9. 2020VocGAN: A High-Fidelity Real-time Vocoder with a Hierarchically-nested Adversarial Networkcited by 26
  10. 2020Universal MelGAN: A Robust Neural Vocoder for High-Fidelity Waveform Generation in Multiple Domainscited by 9
  11. 2020Audio Dequantization for High Fidelity Audio Generation in Flow-based Neural Vocodercited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 2; 2023: 7; 2024: 9; 2025: 3; 2026: 1.

24 papers.

Sort:

By area:

  1. 2021A Survey on Neural Speech Synthesiscited by 182
  2. 2024Recent Advances in Speech Language Models: A Surveycited by 85
  3. 2023HierSpeech++: Bridging the Gap between Semantic and Acoustic Representation of Speech by Hierarchical Variational Inference for Zero-shot Speech Synthesiscited by 35
  4. 2022Avocodo: Generative Adversarial Network for Artifact-free Vocodercited by 18
  5. 2023Let There Be Sound: Reconstructing High Quality Speech from Silent Videoscited by 12
  6. 2024FreGrad: Lightweight and Fast Frequency-aware Diffusion Vocodercited by 11
  7. 2024Accelerating Codec-based Speech Synthesis with Multi-Token Prediction and Speculative Decodingcited by 10
  8. 2023HierVST: Hierarchical Adaptive Zero-shot Voice Style Transfercited by 9
  9. 2022PhaseAug: A Differentiable Augmentation for Speech Synthesis to Simulate One-to-Many Mappingcited by 8
  10. 2025WaveFM: A High-Fidelity and Efficient Vocoder Based on Flow Matchingcited by 7
  11. 2023PauseSpeech: Natural Speech Synthesis via Pre-trained Language Model and Pause-based Prosody Modelingcited by 5
  12. 2024Accelerating High-Fidelity Waveform Generation via Adversarial Flow Matching Optimizationcited by 4
12 more
  1. 2023CrossSpeech: Speaker-independent Acoustic Representation for Cross-lingual Speech Synthesiscited by 3
  2. 2023iSTFTNet2: Faster and More Lightweight iSTFT-Based Neural Vocoder Using 1D-2D CNNcited by 3
  3. 2024AV-GAN: Attention-Based Varifocal Generative Adversarial Network for Uneven Medical Image Translationcited by 3
  4. 2024SINGER: Vivid Audio-driven Singing Video Generation with Multi-scale Spectral Diffusion Modelcited by 1
  5. 2021A Factorization Approach for Motor Imagery Classificationcited by 0
  6. 2023An End-to-End Multi-Module Audio Deepfake Generation System for ADD Challenge 2023cited by 0
  7. 2024Training Generative Adversarial Network-Based Vocoder with Limited Data Using Augmentation-Conditional Discriminatorcited by 0
  8. 2024Dataset Refinement for Improving the Generalization Ability of the EEG Decoding Modelcited by 0
  9. 2024CrossSpeech++: Cross-lingual Speech Synthesis with Decoupled Language and Speaker Generationcited by 0
  10. 2025DPN-GAN: Inducing Periodic Activations in Generative Adversarial Networks for High-Fidelity Audio Synthesiscited by 0
  11. 2025CIS-BWE: Chaos-Informed Speech Bandwidth Extensioncited by 0
  12. 2026ClipTBP: Clip-Pair based Temporal Boundary Prediction with Boundary-Aware Learning for Moment Retrievalcited by 0