Metraipolis › archive › dc_cb0f87ad390d

Shared-State Local Translations for Training-Free Voice Conversion — arXiv:2610.01952

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.01952
License (as archived)
CC0-1.0
Archived
2026-10-07T12:38:41.284Z
SHA-256 of the archived text
f9c4ee6189f4aa22144a22bac46c1094ec7352c01abc074fcb18d084129af5c6
Stable URL of this page
https://metraipolis.com/documento/dc_cb0f87ad390d

How to cite

Shared-State Local Translations for Training-Free Voice Conversion — arXiv:2610.01952 — arXiv (en), https://arxiv.org/abs/2610.01952 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cb0f87ad390d (Metraipolis archive dc_cb0f87ad390d, sha256 f9c4ee6189f4aa22144a22bac46c1094ec7352c01abc074fcb18d084129af5c6)
BibTeX
@misc{dccb0f87ad390d,
  title = {Shared-State Local Translations for Training-Free Voice Conversion — arXiv:2610.01952},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.01952},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cb0f87ad390d; sha256 f9c4ee6189f4aa22144a22bac46c1094ec7352c01abc074fcb18d084129af5c6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.01952. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In one-shot training-free voice conversion (VC), the source and reference utterances may contain different linguistic content, so reliable frame-level correspondence between them cannot be assumed. We propose StateVC, which jointly defines a common set of local regions from pooled frame-level WavLM representations of the source and reference utterances; we refer to these regions as states. These shared states are obtained by fitting a pair-specific Gaussian mixture model to the pooled representations, without explicit source--reference frame matching. Within each state, StateVC estimates a source-to-reference mean shift in the original WavLM space. Source-frame posterior probabilities then combine the state-specific shifts so that different frames can receive different local updates. For the LibriSpeech one-shot protocol, StateVC achieves the lowest word error rate (WER) and character error rate (CER) among the evaluated systems, at 8.01% and 3.22%, respectively, with a speaker similarity (SIM) of 0.9512. It also achieves the highest mean perceived speaker similarity among the evaluated systems and the highest mean naturalness among the evaluated training-free systems.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in eess.AS).
Categorie arXiv: Audio and Speech Processing (eess.AS).
Pagina del lavoro: https://arxiv.org/abs/2610.01952 — 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 2026-10-07T12:11:28.584Z dalla pagina https://arxiv.org/catchup/eess.AS/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).