Metraipolis › archive › dc_89b2aa50e294
One-Step Voice Conversion by Learning kNN Transport in WavLM Space — arXiv:2609.27230
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.27230
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T13:39:32.185Z
- SHA-256 of the archived text
21090ecd87992db2813ac9bdc698135bbfe5faa9be93a5aca9edf9455585ac5b- Stable URL of this page
https://metraipolis.com/documento/dc_89b2aa50e294
How to cite
One-Step Voice Conversion by Learning kNN Transport in WavLM Space — arXiv:2609.27230 — arXiv (en), https://arxiv.org/abs/2609.27230 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_89b2aa50e294 (Metraipolis archive dc_89b2aa50e294, sha256 21090ecd87992db2813ac9bdc698135bbfe5faa9be93a5aca9edf9455585ac5b)
BibTeX
@misc{dc89b2aa50e294,
title = {One-Step Voice Conversion by Learning kNN Transport in WavLM Space — arXiv:2609.27230},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.27230},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_89b2aa50e294; sha256 21090ecd87992db2813ac9bdc698135bbfe5faa9be93a5aca9edf9455585ac5b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.27230. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Voice conversion (VC) systems fall into two families: non-parametric embedding-space methods, which need no trained model but degrade on short target utterances, and spectrogram-based neural architectures, which achieve strong quality via multi-module pipelines with tens of millions of parameters. We propose kNN-FM-VC, a single conditional flow-matching network that learns to approximate the kNN-VC mapping between WavLM embedding distributions of source and target speakers, replacing explicit pointwise kNN matching with a neural regressor trained on kNN-generated pairs. The model is conditioned on the target speaker via cross-attention and FiLM, and trained under three Gaussian conditional paths (Schrödinger bridge, straight line, and constant-variance Gaussian tube), enabling few-step sampling. Unlike Phoneme Hallucinator, which uses an upsampling stage followed by kNN matching, our 13M-parameter model performs conversion with a single learned network and supports one-step inference. On LibriSpeech, the one-step Gaussian Bridge achieves lower WER and higher estimated speech quality than FreeVC and Phoneme Hallucinator. Relative to kNN and kDOT, it substantially reduces WER. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-24 in eess.AS). Categorie arXiv: Audio and Speech Processing (eess.AS). Pagina del lavoro: https://arxiv.org/abs/2609.27230 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T13:17:01.845Z dalla pagina https://arxiv.org/catchup/eess.AS/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).