# Avocodo: Generative Adversarial Network for Artifact-free Vocoder

arXiv: https://arxiv.org/abs/2206.13404 · HTML: https://mlsanity.com/paper/2206.13404/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 47 references that are in the map.
- First posted on arXiv 27 Jun 2022.

## Builds on (most cited first, 28 of 28)

- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [Alias-Free Generative Adversarial Networks](https://mlsanity.com/paper/2106.12423/) (2021)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [FastSpeech 2: Fast and High-Quality End-to-End Text to Speech](https://mlsanity.com/paper/2006.04558/) (2020)
- [Tacotron: Towards End-to-End Speech Synthesis](https://mlsanity.com/paper/1703.10135/) (2017)
- [MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis](https://mlsanity.com/paper/1910.06711/) (2019)
- [Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram](https://mlsanity.com/paper/1910.11480/) (2019)
- [WaveGlow: A Flow-based Generative Network for Speech Synthesis](https://mlsanity.com/paper/1811.00002/) (2018)
- [Adversarial Audio Synthesis](https://mlsanity.com/paper/1802.04208/) (2018)
- [Coupled Generative Adversarial Networks](https://mlsanity.com/paper/1606.07536/) (2016)
- [Parallel WaveNet: Fast High-Fidelity Speech Synthesis](https://mlsanity.com/paper/1711.10433/) (2017)
- [Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separation](https://mlsanity.com/paper/1806.03185/) (2018)
- [Neural Photo Editing with Introspective Adversarial Networks](https://mlsanity.com/paper/1609.07093/) (2016)
- [UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation](https://mlsanity.com/paper/2106.07889/) (2021)
- [Photographic Text-to-Image Synthesis with a Hierarchically-nested Adversarial Network](https://mlsanity.com/paper/1802.09178/) (2018)
- [Multi-band MelGAN: Faster Waveform Generation for High-Quality Text-to-Speech](https://mlsanity.com/paper/2005.05106/) (2020)
- [FloWaveNet : A Generative Flow for Raw Audio](https://mlsanity.com/paper/1811.02155/) (2018)
- [Chunked Autoregressive GAN for Conditional Waveform Synthesis](https://mlsanity.com/paper/2110.10139/) (2021)
- [NU-Wave 2: A General Neural Audio Upsampling Model for Various Sampling Rates](https://mlsanity.com/paper/2206.08545/) (2022)
- [DurIAN: Duration Informed Attention Network For Multimodal Synthesis](https://mlsanity.com/paper/1909.01700/) (2019)
- [Upsampling artifacts in neural audio synthesis](https://mlsanity.com/paper/2010.14356/) (2020)
- [VocGAN: A High-Fidelity Real-time Vocoder with a Hierarchically-nested Adversarial Network](https://mlsanity.com/paper/2007.15256/) (2020)
- [StyleMelGAN: An Efficient High-Fidelity Adversarial Vocoder with Temporal Adaptive Normalization](https://mlsanity.com/paper/2011.01557/) (2020)
- [Fre-GAN: Adversarial Frequency-consistent Audio Synthesis](https://mlsanity.com/paper/2106.02297/) (2021)
- [Daft-Exprt: Cross-Speaker Prosody Transfer on Any Text for Expressive Speech Synthesis](https://mlsanity.com/paper/2108.02271/) (2021)
- [N-Singer: A Non-Autoregressive Korean Singing Voice Synthesis System for Pronunciation Enhancement](https://mlsanity.com/paper/2106.15205/) (2021)

## Built on by (most cited first, 18 of 18)

- [Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis](https://mlsanity.com/paper/2306.00814/) (2023)
- [DDDM-VC: Decoupled Denoising Diffusion Models with Disentangled Representation and Prior Mixup for Verified Robust Voice Conversion](https://mlsanity.com/paper/2305.15816/) (2023)
- [WaveFit: An Iterative and Non-autoregressive Neural Vocoder based on Fixed-Point Iteration](https://mlsanity.com/paper/2210.01029/) (2022)
- [PeriodWave: Multi-Period Flow Matching for High-Fidelity Waveform Generation](https://mlsanity.com/paper/2408.07547/) (2024)
- [Controlling Emotion in Text-to-Speech with Natural Language Prompts](https://mlsanity.com/paper/2406.06406/) (2024)
- [PhaseAug: A Differentiable Augmentation for Speech Synthesis to Simulate One-to-Many Mapping](https://mlsanity.com/paper/2211.04610/) (2022)
- [The IMS Toucan System for the Blizzard Challenge 2023](https://mlsanity.com/paper/2310.17499/) (2023)
- [PITS: Variational Pitch Inference without Fundamental Frequency for End-to-End Pitch-controllable TTS](https://mlsanity.com/paper/2302.12391/) (2023)
- [Lightweight Model Attribution and Detection of Synthetic Speech via Audio Residual Fingerprints](https://mlsanity.com/paper/2411.14013/) (2024)
- [Towards generalizing deep-audio fake detection networks](https://mlsanity.com/paper/2305.13033/) (2023)
- [VIFS: An End-to-End Variational Inference for Foley Sound Synthesis](https://mlsanity.com/paper/2306.05004/) (2023)
- [Controllable Generation of Artificial Speaker Embeddings through Discovery of Principal Directions](https://mlsanity.com/paper/2310.17502/) (2023)
- [JenGAN: Stacked Shifted Filters in GAN-Based Speech Synthesis](https://mlsanity.com/paper/2406.06111/) (2024)
- [Training Universal Vocoders with Feature Smoothing-Based Augmentation Methods for High-Quality TTS Systems](https://mlsanity.com/paper/2409.02517/) (2024)
- [RingFormer: A Neural Vocoder with Ring Attention and Convolution-Augmented Transformer](https://mlsanity.com/paper/2501.01182/) (2025)
- [FNH-TTS: Mixture-of-Experts Duration Modeling for Robust Neural Speech Synthesis](https://mlsanity.com/paper/2508.12001/) (2025)
- [BridgeVoC: Revitalizing Neural Vocoder from a Restoration Perspective](https://mlsanity.com/paper/2511.07116/) (2025)
- [Hearing the Whispers: Black-Box Membership Inference Attacks on Finetuned TTS Models](https://mlsanity.com/paper/2609.01723/) (2026)

## Abstract (arXiv)

Neural vocoders based on the generative adversarial neural network (GAN) have been widely used due to their fast inference speed and lightweight networks while generating high-quality speech waveforms. Since the perceptually important speech components are primarily concentrated in the low-frequency bands, most GAN-based vocoders perform multi-scale analysis that evaluates downsampled speech waveforms. This multi-scale analysis helps the generator improve speech intelligibility. However, in preliminary experiments, we discovered that the multi-scale analysis which focuses on the low-frequency bands causes unintended artifacts, e.g., aliasing and imaging artifacts, which degrade the synthesized speech waveform quality. Therefore, in this paper, we investigate the relationship between these artifacts and GAN-based vocoders and propose a GAN-based vocoder, called Avocodo, that allows the synthesis of high-fidelity speech with reduced artifacts. We introduce two kinds of discriminators to evaluate speech waveforms in various perspectives: a collaborative multi-band discriminator and a sub-band discriminator. We also utilize a pseudo quadrature mirror filter bank to obtain downsampled multi-band speech waveforms while avoiding aliasing. According to experimental results, Avocodo outperforms baseline GAN-based vocoders, both objectively and subjectively, while reproducing speech with fewer artifacts.