# Audio inpainting with generative adversarial network

arXiv: https://arxiv.org/abs/2003.07704 · HTML: https://mlsanity.com/paper/2003.07704/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Mar 2020.

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

- [AUDIT: Audio Editing by Following Instructions with Latent Diffusion Models](https://mlsanity.com/paper/2304.00830/) (2023)
- [Catch-A-Waveform: Learning to Generate Audio from a Single Short Example](https://mlsanity.com/paper/2106.06426/) (2021)
- [Speech inpainting: Context-based speech synthesis guided by video](https://mlsanity.com/paper/2306.00489/) (2023)
- [Token-Based Audio Inpainting via Discrete Diffusion](https://mlsanity.com/paper/2507.08333/) (2025)
- [SHIELD: A Secure and Highly Enhanced Integrated Learning for Robust Deepfake Detection against Adversarial Attacks](https://mlsanity.com/paper/2507.13170/) (2025)
- [Active Restoration of Lost Audio Signals Using Machine Learning and Latent Information](https://mlsanity.com/paper/2111.10891/) (2021)
- [Robust Multi-Modal Speech In-Painting: A Sequence-to-Sequence Approach](https://mlsanity.com/paper/2406.00901/) (2024)
- [Sequence-to-Sequence Multi-Modal Speech In-Painting](https://mlsanity.com/paper/2406.01321/) (2024)

## Abstract (arXiv)

We study the ability of Wasserstein Generative Adversarial Network (WGAN) to generate missing audio content which is, in context, (statistically similar) to the sound and the neighboring borders. We deal with the challenge of audio inpainting long range gaps (500 ms) using WGAN models. We improved the quality of the inpainting part using a new proposed WGAN architecture that uses a short-range and a long-range neighboring borders compared to the classical WGAN model. The performance was compared with two different audio instruments (piano and guitar) and on virtuoso pianists together with a string orchestra. The objective difference grading (ODG) was used to evaluate the performance of both architectures. The proposed model outperforms the classical WGAN model and improves the reconstruction of high-frequency content. Further, we got better results for instruments where the frequency spectrum is mainly in the lower range where small noises are less annoying for human ear and the inpainting part is more perceptible. Finally, we could show that better test results for audio dataset were reached where a particular instrument is accompanist by other instruments if we train the network only on this particular instrument neglecting the other instruments.