mlsanityData to 14 Oct 2026

PhaseAug: A Differentiable Augmentation for Speech Synthesis to Simulate One-to-Many Mapping

arXiv 2211.04610 ↗First posted 8 Nov 2022eess.AS cs.AI cs.SDcited by 8

Not on the map. Why?

Abstract (arXiv)

Previous generative adversarial network (GAN)-based neural vocoders are trained to reconstruct the exact ground truth waveform from the paired mel-spectrogram and do not consider the one-to-many relationship of speech synthesis. This conventional training causes overfitting for both the discriminators and the generator, leading to the periodicity artifacts in the generated audio signal. In this work, we present PhaseAug, the first differentiable augmentation for speech synthesis that rotates the phase of each frequency bin to simulate one-to-many mapping. With our proposed method, we outperform baselines without any architecture modification. Code and audio samples will be available at https://github.com/mindslab-ai/phaseaug.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 17 of its 22 references that are in the map. First posted on arXiv 8 Nov 2022.

Builds on

17 of 22 references.

References · 17

  1. 2020Training Generative Adversarial Networks with Limited Datacited by 1,186
  2. 2021Alias-Free Generative Adversarial Networkscited by 1,184
  3. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,154
  4. 2021Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speechcited by 561
  5. 2020Differentiable Augmentation for Data-Efficient GAN Trainingcited by 363
  6. 2019MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesiscited by 354
  7. 2019Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogramcited by 340
  8. 2022BigVGAN: A Universal Neural Vocoder with Large-Scale Trainingcited by 251
  9. 2018CREPE: A Convolutional Representation for Pitch Estimationcited by 110
  10. 2021Neural Analysis and Synthesis: Reconstructing Speech from Self-Supervised Representationscited by 81
  11. 2021NU-Wave: A Diffusion Probabilistic Model for Neural Audio Upsamplingcited by 50
  12. 2021Chunked Autoregressive GAN for Conditional Waveform Synthesiscited by 38
5 more
  1. 2022NU-Wave 2: A General Neural Audio Upsampling Model for Various Sampling Ratescited by 36
  2. 2020VocGAN: A High-Fidelity Real-time Vocoder with a Hierarchically-nested Adversarial Networkcited by 26
  3. 2021Fre-GAN: Adversarial Frequency-consistent Audio Synthesiscited by 24
  4. 2022Avocodo: Generative Adversarial Network for Artifact-free Vocodercited by 18
  5. 2020TTS-by-TTS: TTS-driven Data Augmentation for Fast and High-Quality Speech Synthesiscited by 15

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 2; 2025: 2; 2026: 1.

8 papers.

  1. 2023PITS: Variational Pitch Inference without Fundamental Frequency for End-to-End Pitch-controllable TTScited by 4
  2. 2025EDNet: A Versatile Speech Enhancement Framework with Gating Mamba Mechanism and Phase Shift-Invariant Trainingcited by 3
  3. 2023VIFS: An End-to-End Variational Inference for Foley Sound Synthesiscited by 2
  4. 2026Reconstruct! Don't Encode: Self-Supervised Representation Reconstruction Loss for High-Intelligibility and Low-Latency Streaming Neural Audio Codeccited by 2
  5. 2023PhasePerturbation: Speech Data Augmentation via Phase Perturbation for Automatic Speech Recognitioncited by 1
  6. 2025MaskVCT: Masked Voice Codec Transformer for Zero-Shot Voice Conversion With Increased Controllability via Multiple Guidancescited by 1
  7. 2024Training Generative Adversarial Network-Based Vocoder with Limited Data Using Augmentation-Conditional Discriminatorcited by 0
  8. 2024JenGAN: Stacked Shifted Filters in GAN-Based Speech Synthesiscited by 0