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

TL;DR

MelGAN-VC introduces a non-parallel, GAN-based voice and audio style transfer method capable of converting arbitrarily long samples, including speech and music, while preserving content and style effectively.

Contribution

It presents a novel non-parallel voice conversion framework using GANs and a siamese network, extending to music style transfer for arbitrary-length audio.

Findings

Effective voice conversion with non-parallel data

Successful style transfer for speech and music

Works on arbitrarily long audio samples

Abstract

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.