Search Results for author: Marco Pasini

Found 3 papers, 2 papers with code

Bass Accompaniment Generation via Latent Diffusion

no code implementations2 Feb 2024 Marco Pasini, Maarten Grachten, Stefan Lattner

At the core of our method are audio autoencoders that efficiently compress audio waveform samples into invertible latent representations, and a conditional latent diffusion model that takes as input the latent encoding of a mix and generates the latent encoding of a corresponding stem.

Audio Generation

Musika! Fast Infinite Waveform Music Generation

1 code implementation18 Aug 2022 Marco Pasini, Jan Schlüter

We release the source code and pretrained autoencoder weights at github. com/marcoppasini/musika, such that a GAN can be trained on a new music domain with a single GPU in a matter of hours.

Generative Adversarial Network Music Generation

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

2 code implementations8 Oct 2019 Marco Pasini

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.

Generative Adversarial Network Music Style Transfer +3

Cannot find the paper you are looking for? You can Submit a new open access paper.