Perceptually Aligned Music2Latent
This repository contains weights for the perceptually aligned Music2Latent and autoregressive rectified flow models as described in Perceptually Aligning Representations of Music via Noise-Augmented Autoencoders, Bjare et al., NeurIPS - AI for Music Workshop, 2025.
If you use this project in your research, please cite the following paper:
@inproceedings{
bjare2025perceptually,
title={Perceptually Aligning Representations of Music via Noise-Augmented Autoencoders},
author={Mathias Rose Bjare and Giorgia Cantisani and Marco Pasini and Stefan Lattner and Gerhard Widmer},
booktitle={NeurIPS - AI for Music Workshop},
year={2025},
url={https://openreview.net/forum?id=rXUKO0ysUy}
}
License
This library is released under the CC BY-NC 4.0 license. Please refer to the LICENSE file for more details.
To obtain a commercial license, please contact music@csl.sony.fr.
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support