# StyleMelGAN: An Efficient High-Fidelity Adversarial Vocoder with Temporal Adaptive Normalization

arXiv: https://arxiv.org/abs/2011.01557 · HTML: https://mlsanity.com/paper/2011.01557/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Nov 2020.

## Built on by (most cited first, 26 of 26)

- [BigVGAN: A Universal Neural Vocoder with Large-Scale Training](https://mlsanity.com/paper/2206.04658/) (2022)
- [SVTS: Scalable Video-to-Speech Synthesis](https://mlsanity.com/paper/2205.02058/) (2022)
- [iSTFTNet: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse Short-Time Fourier Transform](https://mlsanity.com/paper/2203.02395/) (2022)
- [ESPnet2-TTS: Extending the Edge of TTS Research](https://mlsanity.com/paper/2110.07840/) (2021)
- [SafeEar: Content Privacy-Preserving Audio Deepfake Detection](https://mlsanity.com/paper/2409.09272/) (2024)
- [Avocodo: Generative Adversarial Network for Artifact-free Vocoder](https://mlsanity.com/paper/2206.13404/) (2022)
- [An Initial Investigation for Detecting Vocoder Fingerprints of Fake Audio](https://mlsanity.com/paper/2208.09646/) (2022)
- [Source-Filter HiFi-GAN: Fast and Pitch Controllable High-Fidelity Neural Vocoder](https://mlsanity.com/paper/2210.15533/) (2022)
- [VNet: A GAN-based Multi-Tier Discriminator Network for Speech Synthesis Vocoders](https://mlsanity.com/paper/2408.06906/) (2024)
- [A Streamwise GAN Vocoder for Wideband Speech Coding at Very Low Bit Rate](https://mlsanity.com/paper/2108.04051/) (2021)
- [Wave-U-Net Discriminator: Fast and Lightweight Discriminator for Generative Adversarial Network-Based Speech Synthesis](https://mlsanity.com/paper/2303.13909/) (2023)
- [iSTFTNet2: Faster and More Lightweight iSTFT-Based Neural Vocoder Using 1D-2D CNN](https://mlsanity.com/paper/2308.07117/) (2023)
- [Large-scale unsupervised audio pre-training for video-to-speech synthesis](https://mlsanity.com/paper/2306.15464/) (2023)
- [Rapid Speaker Adaptation in Low Resource Text to Speech Systems using Synthetic Data and Transfer learning](https://mlsanity.com/paper/2312.01107/) (2023)
- [Framewise WaveGAN: High Speed Adversarial Vocoder in Time Domain with Very Low Computational Complexity](https://mlsanity.com/paper/2212.04532/) (2022)
- [GANetic Loss for Generative Adversarial Networks with a Focus on Medical Applications](https://mlsanity.com/paper/2406.05023/) (2024)
- [Real-Time Streaming Mel Vocoding with Generative Flow Matching](https://mlsanity.com/paper/2509.15085/) (2025)
- [Improving the expressiveness of neural vocoding with non-affine Normalizing Flows](https://mlsanity.com/paper/2106.08649/) (2021)
- [FlowVocoder: A small Footprint Neural Vocoder based Normalizing flow for Speech Synthesis](https://mlsanity.com/paper/2109.13675/) (2021)
- [WOLONet: Wave Outlooker for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2206.09920/) (2022)
- [Enhancing Speech-to-Speech Translation with Multiple TTS Targets](https://mlsanity.com/paper/2304.04618/) (2023)
- [Code-Mixed Text to Speech Synthesis under Low-Resource Constraints](https://mlsanity.com/paper/2312.01103/) (2023)
- [Training Generative Adversarial Network-Based Vocoder with Limited Data Using Augmentation-Conditional Discriminator](https://mlsanity.com/paper/2403.16464/) (2024)
- [Enhancing Kurdish Text-to-Speech with Native Corpus Training: A High-Quality WaveGlow Vocoder Approach](https://mlsanity.com/paper/2409.13734/) (2024)
- [DPN-GAN: Inducing Periodic Activations in Generative Adversarial Networks for High-Fidelity Audio Synthesis](https://mlsanity.com/paper/2505.09091/) (2025)
- [AUDETER: A Large-scale Dataset for Deepfake Audio Detection in Open Worlds](https://mlsanity.com/paper/2509.04345/) (2025)

## Abstract (arXiv)

In recent years, neural vocoders have surpassed classical speech generation approaches in naturalness and perceptual quality of the synthesized speech. Computationally heavy models like WaveNet and WaveGlow achieve best results, while lightweight GAN models, e.g. MelGAN and Parallel WaveGAN, remain inferior in terms of perceptual quality. We therefore propose StyleMelGAN, a lightweight neural vocoder allowing synthesis of high-fidelity speech with low computational complexity. StyleMelGAN employs temporal adaptive normalization to style a low-dimensional noise vector with the acoustic features of the target speech. For efficient training, multiple random-window discriminators adversarially evaluate the speech signal analyzed by a filter bank, with regularization provided by a multi-scale spectral reconstruction loss. The highly parallelizable speech generation is several times faster than real-time on CPUs and GPUs. MUSHRA and P.800 listening tests show that StyleMelGAN outperforms prior neural vocoders in copy-synthesis and Text-to-Speech scenarios.