# Chunked Autoregressive GAN for Conditional Waveform Synthesis

arXiv: https://arxiv.org/abs/2110.10139 · HTML: https://mlsanity.com/paper/2110.10139/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Oct 2021.

## Built on by (most cited first, 30 of 38)

- [High-Fidelity Audio Compression with Improved RVQGAN](https://mlsanity.com/paper/2306.06546/) (2023)
- [BigVGAN: A Universal Neural Vocoder with Large-Scale Training](https://mlsanity.com/paper/2206.04658/) (2022)
- [Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis](https://mlsanity.com/paper/2306.00814/) (2023)
- [Multi-instrument Music Synthesis with Spectrogram Diffusion](https://mlsanity.com/paper/2206.05408/) (2022)
- [HierSpeech++: Bridging the Gap between Semantic and Acoustic Representation of Speech by Hierarchical Variational Inference for Zero-shot Speech Synthesis](https://mlsanity.com/paper/2311.12454/) (2023)
- [Autoregressive Diffusion Transformer for Text-to-Speech Synthesis](https://mlsanity.com/paper/2406.05551/) (2024)
- [textless-lib: a Library for Textless Spoken Language Processing](https://mlsanity.com/paper/2202.07359/) (2022)
- [Avocodo: Generative Adversarial Network for Artifact-free Vocoder](https://mlsanity.com/paper/2206.13404/) (2022)
- [PeriodWave: Multi-Period Flow Matching for High-Fidelity Waveform Generation](https://mlsanity.com/paper/2408.07547/) (2024)
- [VNet: A GAN-based Multi-Tier Discriminator Network for Speech Synthesis Vocoders](https://mlsanity.com/paper/2408.06906/) (2024)
- [HiddenSinger: High-Quality Singing Voice Synthesis via Neural Audio Codec and Latent Diffusion Models](https://mlsanity.com/paper/2306.06814/) (2023)
- [RFWave: Multi-band Rectified Flow for Audio Waveform Reconstruction](https://mlsanity.com/paper/2403.05010/) (2024)
- [PhaseAug: A Differentiable Augmentation for Speech Synthesis to Simulate One-to-Many Mapping](https://mlsanity.com/paper/2211.04610/) (2022)
- [WaveFM: A High-Fidelity and Efficient Vocoder Based on Flow Matching](https://mlsanity.com/paper/2503.16689/) (2025)
- [Period VITS: Variational Inference with Explicit Pitch Modeling for End-to-end Emotional Speech Synthesis](https://mlsanity.com/paper/2210.15964/) (2022)
- [BigVSAN: Enhancing GAN-based Neural Vocoders with Slicing Adversarial Network](https://mlsanity.com/paper/2309.02836/) (2023)
- [Iterative autoregression: a novel trick to improve your low-latency speech enhancement model](https://mlsanity.com/paper/2211.01751/) (2022)
- [Fast, High-Quality and Parameter-Efficient Articulatory Synthesis using Differentiable DSP](https://mlsanity.com/paper/2409.02451/) (2024)
- [Reproducible Subjective Evaluation](https://mlsanity.com/paper/2203.04444/) (2022)
- [Mel Spectrogram Inversion with Stable Pitch](https://mlsanity.com/paper/2208.12782/) (2022)
- [VAKTA-SETU: A Speech-to-Speech Machine Translation Service in Select Indic Languages](https://mlsanity.com/paper/2305.12518/) (2023)
- [Towards Robust FastSpeech 2 by Modelling Residual Multimodality](https://mlsanity.com/paper/2306.01442/) (2023)
- [Autoregressive GAN for Semantic Unconditional Head Motion Generation](https://mlsanity.com/paper/2211.00987/) (2022)
- [PhasePerturbation: Speech Data Augmentation via Phase Perturbation for Automatic Speech Recognition](https://mlsanity.com/paper/2312.08571/) (2023)
- [EVA-GAN: Enhanced Various Audio Generation via Scalable Generative Adversarial Networks](https://mlsanity.com/paper/2402.00892/) (2024)
- [R-MelNet: Reduced Mel-Spectral Modeling for Neural TTS](https://mlsanity.com/paper/2206.15276/) (2022)
- [DisfluencyFixer: A tool to enhance Language Learning through Speech To Speech Disfluency Correction](https://mlsanity.com/paper/2305.16957/) (2023)
- [Training Generative Adversarial Network-Based Vocoder with Limited Data Using Augmentation-Conditional Discriminator](https://mlsanity.com/paper/2403.16464/) (2024)
- [JenGAN: Stacked Shifted Filters in GAN-Based Speech Synthesis](https://mlsanity.com/paper/2406.06111/) (2024)
- [DPN-GAN: Inducing Periodic Activations in Generative Adversarial Networks for High-Fidelity Audio Synthesis](https://mlsanity.com/paper/2505.09091/) (2025)

## Abstract (arXiv)

Conditional waveform synthesis models learn a distribution of audio waveforms given conditioning such as text, mel-spectrograms, or MIDI. These systems employ deep generative models that model the waveform via either sequential (autoregressive) or parallel (non-autoregressive) sampling. Generative adversarial networks (GANs) have become a common choice for non-autoregressive waveform synthesis. However, state-of-the-art GAN-based models produce artifacts when performing mel-spectrogram inversion. In this paper, we demonstrate that these artifacts correspond with an inability for the generator to learn accurate pitch and periodicity. We show that simple pitch and periodicity conditioning is insufficient for reducing this error relative to using autoregression. We discuss the inductive bias that autoregression provides for learning the relationship between instantaneous frequency and phase, and show that this inductive bias holds even when autoregressively sampling large chunks of the waveform during each forward pass. Relative to prior state-of-the-art GAN-based models, our proposed model, Chunked Autoregressive GAN (CARGAN) reduces pitch error by 40-60%, reduces training time by 58%, maintains a fast generation speed suitable for real-time or interactive applications, and maintains or improves subjective quality.