# Generative adversarial network-based approach to signal reconstruction from magnitude spectrograms

arXiv: https://arxiv.org/abs/1804.02181 · HTML: https://mlsanity.com/paper/1804.02181/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Apr 2018.

## Built on by (most cited first, 8 of 8)

- [Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis](https://mlsanity.com/paper/2306.00814/) (2023)
- [iSTFTNet: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse Short-Time Fourier Transform](https://mlsanity.com/paper/2203.02395/) (2022)
- [Audio representations for deep learning in sound synthesis: A review](https://mlsanity.com/paper/2201.02490/) (2022)
- [DiffPhase: Generative Diffusion-based STFT Phase Retrieval](https://mlsanity.com/paper/2211.04332/) (2022)
- [iSTFTNet2: Faster and More Lightweight iSTFT-Based Neural Vocoder Using 1D-2D CNN](https://mlsanity.com/paper/2308.07117/) (2023)
- [A Survey of Deep Learning for Complex Speech Spectrograms](https://mlsanity.com/paper/2505.08694/) (2025)
- [Vocoder-Projected Feature Discriminator](https://mlsanity.com/paper/2508.17874/) (2025)
- [Toward Complex-Valued Neural Networks for Waveform Generation](https://mlsanity.com/paper/2603.11589/) (2026)

## Abstract (arXiv)

In this paper, we address the problem of reconstructing a time-domain signal (or a phase spectrogram) solely from a magnitude spectrogram. Since magnitude spectrograms do not contain phase information, we must restore or infer phase information to reconstruct a time-domain signal. One widely used approach for dealing with the signal reconstruction problem was proposed by Griffin and Lim. This method usually requires many iterations for the signal reconstruction process and depending on the inputs, it does not always produce high-quality audio signals. To overcome these shortcomings, we apply a learning-based approach to the signal reconstruction problem by modeling the signal reconstruction process using a deep neural network and training it using the idea of a generative adversarial network. Experimental evaluations revealed that our method was able to reconstruct signals faster with higher quality than the Griffin-Lim method.