# Self-Supervised VQ-VAE for One-Shot Music Style Transfer

Source: [Self-Supervised VQ-VAE for One-Shot Music Style Transfer](<https://www.sota2.com/research/paper/68fa6a1e1e209131cea260dc>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:16:37.291Z

Authors: Ond\\v{r}ej C\\'ifka, Alexey Ozerov, Umut \\c{S}im\\c{s}ekli, Ga\\"el Richard

Published: 2021-02-10T21:42:49.000Z

## Abstract

Neural style transfer, allowing to apply the artistic style of one image to another, has become one of the most widely showcased computer vision applications shortly after its introduction. In contrast, related tasks in the music audio domain remained, until recently, largely untackled. While several style conversion methods tailored to musical signals have been proposed, most lack the 'one-shot' capability of classical image style transfer algorithms. On the other hand, the results of existing one-shot audio style transfer methods on musical inputs are not as compelling. In this work, we are specifically interested in the problem of one-shot timbre transfer. We present a novel method for this task, based on an extension of the vector-quantized variational autoencoder (VQ-VAE), along with a simple self-supervised learning strategy designed to obtain disentangled representations of timbre and pitch. We evaluate the method using a set of objective metrics and show that it is able to outperform selected baselines.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Multi-instrument timbre transfer on CocoChorales self-reconstruction](<https://www.sota2.com/research/sota/multi-instrument-timbre-transfer-on-cocochorales-self-reconstruction.md>): Multi-instrument timbre transfer; CocoChorales self-reconstruction; FAD: 0.536.

- [Multi-instrument Timbre Transfer on CocoChorales cross-timbre transfer](<https://www.sota2.com/research/sota/multi-instrument-timbre-transfer-on-cocochorales-cross-timbre-transfer.md>): Multi-instrument timbre transfer; CocoChorales cross-timbre transfer; FAD: 0.643.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2102.05749>)

[PDF](<https://arxiv.org/pdf/2102.05749.pdf>)