Metraipolis › archive › dc_656505bbca8b
Partial Accent-Control Editing in Frozen Speech Representations for Accent Conversion — arXiv:2609.22031
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.22031
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-10T03:12:20.239Z
- SHA-256 of the archived text
7900d472a5bd4909ead844a9aa698615b2fd5da3669ed6810d3b69b1b9800336- Stable URL of this page
https://metraipolis.com/documento/dc_656505bbca8b
How to cite
Partial Accent-Control Editing in Frozen Speech Representations for Accent Conversion — arXiv:2609.22031 — arXiv (en), https://arxiv.org/abs/2609.22031 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_656505bbca8b (Metraipolis archive dc_656505bbca8b, sha256 7900d472a5bd4909ead844a9aa698615b2fd5da3669ed6810d3b69b1b9800336)
BibTeX
@misc{dc656505bbca8b,
title = {Partial Accent-Control Editing in Frozen Speech Representations for Accent Conversion — arXiv:2609.22031},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.22031},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_656505bbca8b; sha256 7900d472a5bd4909ead844a9aa698615b2fd5da3669ed6810d3b69b1b9800336},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.22031. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Accent conversion is the task of modifying a speech recording so that it sounds closer to a target accent while preserving linguistic content and other speaker-related characteristics. Most accent conversion systems use trained, generative models. Although they can induce target-accented speech, the strength of accent modification is not controllable at inference time, making it difficult to analyse how the strength of accent conversion affects source preservation. We propose Partial Accent-Control Editing (PACE), an accent conversion framework based upon the editing of frozen WavLM representations without the training of an accent-conditioned generator. A constrained edit is first applied to source WavLM features, which are then fused with target-accent reference features retrieved from non-parallel accent examples. Fusion weights are used to control the trade-off between accent conversion strength and the degradation of other source attributes. Using a suite of five metrics, and with the cost of accent-entangled speaker similarity, we show that PACE is substantially superior to a pair of competitive baselines in terms of both accent conversion and source preservation. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-21 in eess.AS). Categorie arXiv: Audio and Speech Processing (eess.AS). Pagina del lavoro: https://arxiv.org/abs/2609.22031 — 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 2026-10-10T03:01:34.419Z dalla pagina https://arxiv.org/catchup/eess.AS/2026-09-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).