Metraipolis › archive › dc_bfba17f432eb

AccentCanvas: Activity-Guided Bidirectional Accent Conversion — arXiv:2611.08972

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.08972
License (as archived)
CC0-1.0
Archived
2026-11-09T23:04:20.500Z
SHA-256 of the archived text
44bd78ede21668d6249f30c0c61c9cb3d0bc6062feb8c41b056e607eb31be02a
Stable URL of this page
https://metraipolis.com/documento/dc_bfba17f432eb

How to cite

AccentCanvas: Activity-Guided Bidirectional Accent Conversion — arXiv:2611.08972 — arXiv (en), https://arxiv.org/abs/2611.08972 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bfba17f432eb (Metraipolis archive dc_bfba17f432eb, sha256 44bd78ede21668d6249f30c0c61c9cb3d0bc6062feb8c41b056e607eb31be02a)
BibTeX
@misc{dcbfba17f432eb,
  title = {AccentCanvas: Activity-Guided Bidirectional Accent Conversion — arXiv:2611.08972},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.08972},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bfba17f432eb; sha256 44bd78ede21668d6249f30c0c61c9cb3d0bc6062feb8c41b056e607eb31be02a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.08972. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Accent conversion for dubbing must change pronunciation while preserving content, voice, and source timing. Normalization alone cannot produce requested non-native accents, and matching total duration does not ensure local speech/pause alignment. We present AccentCanvas, a shared discrete diffusion model for normalization and L1-to-L2 conversion, trained on cross-paired shared-prompt recordings and synthetic pairs. Frame-level speech activity and repetition-preserving units guide local timing through synthesis. Across both tasks, AccentCanvas achieves the highest accent conversion performance (Accent Arrival) and mean listener-rated accent similarity among compared systems, with over 73% lower speech-boundary error than the best baseline for each task. These gains accompany higher L1-to-L2 WER than TokAN and Vevo-Style, highlighting a tradeoff between requested-accent resemblance and ASR-based content recognition. this https URL

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv eess.AS, nuovi lavori del giorno).
Categorie arXiv: Audio and Speech Processing (eess.AS).
Pagina del lavoro: https://arxiv.org/abs/2611.08972 — 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 2026-11-09T22:59:22.096Z dalla pagina https://arxiv.org/list/eess.AS/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).