# MelGAN-VC: Voice Conversion and Audio Style Transfer on arbitrarily long samples using Spectrograms

arXiv: https://arxiv.org/abs/1910.03713 · HTML: https://mlsanity.com/paper/1910.03713/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Oct 2019.

## Built on by (most cited first, 12 of 12)

- [AUDIT: Audio Editing by Following Instructions with Latent Diffusion Models](https://mlsanity.com/paper/2304.00830/) (2023)
- [Musika! Fast Infinite Waveform Music Generation](https://mlsanity.com/paper/2208.08706/) (2022)
- [Towards General-Purpose Text-Instruction-Guided Voice Conversion](https://mlsanity.com/paper/2309.14324/) (2023)
- [RefineGAN: Universally Generating Waveform Better than Ground Truth with Highly Accurate Pitch and Intensity Responses](https://mlsanity.com/paper/2111.00962/) (2021)
- [An Adaptive Learning based Generative Adversarial Network for One-To-One Voice Conversion](https://mlsanity.com/paper/2104.12159/) (2021)
- [Generative Adversarial Network based Voice Conversion: Techniques, Challenges, and Recent Advancements](https://mlsanity.com/paper/2504.19197/) (2025)
- [Music Sentiment Transfer](https://mlsanity.com/paper/2110.05765/) (2021)
- [A Comparative Analysis Of Latent Regressor Losses For Singing Voice Conversion](https://mlsanity.com/paper/2302.13678/) (2023)
- [Collective Learning Mechanism based Optimal Transport Generative Adversarial Network for Non-parallel Voice Conversion](https://mlsanity.com/paper/2504.13791/) (2025)
- [Voice Aging with Audio-Visual Style Transfer](https://mlsanity.com/paper/2110.02411/) (2021)
- [Can Machines Generate Personalized Music? A Hybrid Favorite-aware Method for User Preference Music Transfer](https://mlsanity.com/paper/2201.08526/) (2022)
- [Read it to me: An emotionally aware Speech Narration Application](https://mlsanity.com/paper/2209.02785/) (2022)

## Abstract (arXiv)

Traditional voice conversion methods rely on parallel recordings of multiple speakers pronouncing the same sentences. For real-world applications however, parallel data is rarely available. We propose MelGAN-VC, a voice conversion method that relies on non-parallel speech data and is able to convert audio signals of arbitrary length from a source voice to a target voice. We firstly compute spectrograms from waveform data and then perform a domain translation using a Generative Adversarial Network (GAN) architecture. An additional siamese network helps preserving speech information in the translation process, without sacrificing the ability to flexibly model the style of the target speaker. We test our framework with a dataset of clean speech recordings, as well as with a collection of noisy real-world speech examples. Finally, we apply the same method to perform music style transfer, translating arbitrarily long music samples from one genre to another, and showing that our framework is flexible and can be used for audio manipulation applications different from voice conversion.