8000 GitHub - ishine/mkl-vc: [Interspeech 2025] Official implementation of "Training-Free Voice Conversion with Factorized Optimal Transport"
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content
/ mkl-vc Public
forked from alobashev/mkl-vc

[Interspeech 2025] Official implementation of "Training-Free Voice Conversion with Factorized Optimal Transport"

Notifications You must be signed in to change notification settings

ishine/mkl-vc

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

16 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Training-Free Voice Conversion with Factorized Optimal Transport [Interspeech 2025]

By Alexander Lobashev, Assel Yermekova, Maria Larchenko

arXiv

graphical_abstract We introduce Factorized MKL-VC, a training-free modification for kNN-VC pipeline. In contrast with original pipeline, our algorithm performs high quality any-to-any cross-lingual voice conversion with only 5 second of reference audio. MKL-VC replaces kNN regression with a factorized optimal transport map in WavLM embedding subspaces, derived from Monge-Kantorovich Linear solution. Factorization addresses non-uniform variance across dimensions, ensuring effective feature transformation. Experiments on LibriSpeech and FLEURS datasets show MKL-VC significantly improves content preservation and robustness with short reference audio, outperforming kNN-VC. MKL-VC achieves performance comparable to FACodec, especially in cross-lingual voice conversion domain.

This repository contains the source code and instructions for reproducing the results presented in our paper.

Citation

@inproceedings{
alobashev25,
title={Training-Free Voice Conversion with Factorized Optimal Transport},
author={Alexander Lobashev and Assel Yermekova and Maria Larchenko},
booktitle={Twenty sixth edition of the Interspeech Conference},
year={2025},
url={https://www.arxiv.org/abs/2506.09709}
}

About

[Interspeech 2025] Official implementation of "Training-Free Voice Conversion with Factorized Optimal Transport"

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 95.3%
  • Python 4.7%
0