Music Style Transfer

8 papers with code • 0 benchmarks • 3 datasets

This task has no description! Would you like to contribute one?

Most implemented papers

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

marcoppasini/MelGAN-VC 8 Oct 2019

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.

Groove2Groove: One-Shot Music Style Transfer with Supervision from Synthetic Data

cifkao/groove2groove IEEE/ACM Transactions on Audio, Speech, and Language Processing 2020

Style transfer is the process of changing the style of an image, video, audio clip or musical piece so as to match the style of a given example.

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

cifkao/ss-vq-vae 10 Feb 2021

While several style conversion methods tailored to musical signals have been proposed, most lack the 'one-shot' capability of classical image style transfer algorithms.

MuseMorphose: Full-Song and Fine-Grained Piano Music Style Transfer with One Transformer VAE

YatingMusic/MuseMorphose 10 May 2021

Transformers and variational autoencoders (VAE) have been extensively employed for symbolic (e. g., MIDI) domain music generation.

DadaGP: A Dataset of Tokenized GuitarPro Songs for Sequence Models

dada-bots/dadaGP 30 Jul 2021

In this work, we present DadaGP, a new symbolic music dataset comprising 26, 181 song scores in the GuitarPro format covering 739 musical genres, along with an accompanying tokenized format well-suited for generative sequence models such as the Transformer.

Actions Speak Louder than Listening: Evaluating Music Style Transfer based on Editing Experience

s603122001/Bidirectional-Music-Style-Transformer 25 Oct 2021

In this paper, we propose an editing test to evaluate users' editing experience of music generation models in a systematic way.

Can Machines Generate Personalized Music? A Hybrid Favorite-aware Method for User Preference Music Transfer

zhejinghu/upmt 21 Jan 2022

User preference music transfer (UPMT) is a new problem in music style transfer that can be applied to many scenarios but remains understudied.

Msanii: High Fidelity Music Synthesis on a Shoestring Budget

kinyugo/msanii 16 Jan 2023

In this paper, we present Msanii, a novel diffusion-based model for synthesizing long-context, high-fidelity music efficiently.

A Dataset and Baselines for Measuring and Predicting the Music Piece Memorability

no code yet • 21 May 2024

Despite the abundance of music, certain pieces remain more memorable and often gain greater popularity.