mlsanityData to 14 Oct 2026

Training-Free Voice Conversion with Factorized Optimal Transport

arXiv 2506.09709 ↗First posted 11 Jun 2025cs.SD cs.CV cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

This paper introduces 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.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 13 of its 19 references that are in the map. First posted on arXiv 11 Jun 2025.

Builds on

13 of 19 references.

References · 13

  1. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  2. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,342
  3. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,316
  4. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,657
  5. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,154
  6. 2022FLEURS: Few-shot Learning Evaluation of Universal Representations of Speechcited by 469
  7. 2021YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyonecited by 278
  8. 2024NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Modelscited by 226
  9. 2020An Overview of Voice Conversion and its Challenges: From Statistical Modeling to Deep Learningcited by 112
  10. 2021Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Schemecited by 100
  11. 2022FreeVC: Towards High-Quality Text-Free One-Shot Voice Conversioncited by 80
  12. 2023Voice Conversion With Just Nearest Neighborscited by 68
1 more
  1. 2021VQMIVC: Vector Quantization and Mutual Information-Based Unsupervised Speech Representation Disentanglement for One-shot Voice Conversioncited by 64

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025Provable Speech Attributes Conversion via Latent Independencecited by 1
  2. 2025Discrete optimal transport is a strong audio adversarial attackcited by 0