# Expediting TTS Synthesis with Adversarial Vocoding

arXiv: https://arxiv.org/abs/1904.07944 · HTML: https://mlsanity.com/paper/1904.07944/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Apr 2019.

## Built on by (most cited first, 10 of 10)

- [A Survey on Neural Speech Synthesis](https://mlsanity.com/paper/2106.15561/) (2021)
- [It's Raw! Audio Generation with State-Space Models](https://mlsanity.com/paper/2202.09729/) (2022)
- [WaveGuard: Understanding and Mitigating Audio Adversarial Examples](https://mlsanity.com/paper/2103.03344/) (2021)
- [iSTFTNet: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse Short-Time Fourier Transform](https://mlsanity.com/paper/2203.02395/) (2022)
- [Adapting TTS models For New Speakers using Transfer Learning](https://mlsanity.com/paper/2110.05798/) (2021)
- [Expressive Neural Voice Cloning](https://mlsanity.com/paper/2102.00151/) (2021)
- [Audio representations for deep learning in sound synthesis: A review](https://mlsanity.com/paper/2201.02490/) (2022)
- [A Survey of Deep Learning Audio Generation Methods](https://mlsanity.com/paper/2406.00146/) (2024)
- [iSTFTNet2: Faster and More Lightweight iSTFT-Based Neural Vocoder Using 1D-2D CNN](https://mlsanity.com/paper/2308.07117/) (2023)
- [Toward Complex-Valued Neural Networks for Waveform Generation](https://mlsanity.com/paper/2603.11589/) (2026)

## Abstract (arXiv)

Recent approaches in text-to-speech (TTS) synthesis employ neural network strategies to vocode perceptually-informed spectrogram representations directly into listenable waveforms. Such vocoding procedures create a computational bottleneck in modern TTS pipelines. We propose an alternative approach which utilizes generative adversarial networks (GANs) to learn mappings from perceptually-informed spectrograms to simple magnitude spectrograms which can be heuristically vocoded. Through a user study, we show that our approach significantly outperforms na"ive vocoding strategies while being hundreds of times faster than neural network vocoders used in state-of-the-art TTS systems. We also show that our method can be used to achieve state-of-the-art results in unsupervised synthesis of individual words of speech.