Metraipolis › archive › dc_911dc99cb24d

Ruby-OPD: Enhancing Pronunciation Controllability and Accuracy for Flow-Matching Text-to-Speech via On-Policy Distillation — arXiv:2611.06403

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.06403
License (as archived)
CC0-1.0
Archived
2026-11-05T18:18:47.540Z
SHA-256 of the archived text
346492d43e5c68e32d87e1519f0091d0fe5cc4a83cfe83872cd204d4f42a4fcc
Stable URL of this page
https://metraipolis.com/documento/dc_911dc99cb24d

How to cite

Ruby-OPD: Enhancing Pronunciation Controllability and Accuracy for Flow-Matching Text-to-Speech via On-Policy Distillation — arXiv:2611.06403 — arXiv (en), https://arxiv.org/abs/2611.06403 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_911dc99cb24d (Metraipolis archive dc_911dc99cb24d, sha256 346492d43e5c68e32d87e1519f0091d0fe5cc4a83cfe83872cd204d4f42a4fcc)
BibTeX
@misc{dc911dc99cb24d,
  title = {Ruby-OPD: Enhancing Pronunciation Controllability and Accuracy for Flow-Matching Text-to-Speech via On-Policy Distillation — arXiv:2611.06403},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.06403},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_911dc99cb24d; sha256 346492d43e5c68e32d87e1519f0091d0fe5cc4a83cfe83872cd204d4f42a4fcc},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.06403. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Achieving both high pronunciation accuracy and fine-grained controllability remains a central challenge in Japanese text-to-speech (TTS), as Japanese is an unsegmented language mixing logographic Kanji and phonographic Kana with extensive polyphony. Traditional cascaded systems convert text into phoneme sequences via a front-end, ensuring pronunciation control but discarding lexical semantics and prosodic cues in surface orthography. Conversely, recent zero-shot TTS models directly consume raw orthographic text to improve naturalness, yet suffer from polyphone errors and lack explicit pronunciation control. To bridge this gap, we propose a two-stage framework for flow-matching TTS. First, we investigate Ruby text representations with orthography perturbation to jointly preserve surface forms and target pronunciations for reliable control. Second, we introduce On-Policy Distillation (OPD) on large-scale text-only corpora to enhance pronunciation accuracy on raw orthographic text without paired speech. On the Joyo-Kanji-Yomi benchmark, our model achieves 97.13% Accuracy, 2.02% Target PER, 0.70% Sentence PER, and 4.21% Sentence CER under raw text while retaining strong controllability.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2611.06403 — 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 2026-11-05T18:13:03.945Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).