Metraipolis › archive › dc_2e2bc9709bd5
EmpDPO: Enabling Emphasis Control in TTS via Direct Preference Optimization — arXiv:2610.39427
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.39427
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-01T03:01:12.242Z
- SHA-256 of the archived text
dd7abee6838469e5f1544523229f97b9a95dec11e6dc751f460cc0ff7884fa0b- Stable URL of this page
https://metraipolis.com/documento/dc_2e2bc9709bd5
How to cite
EmpDPO: Enabling Emphasis Control in TTS via Direct Preference Optimization — arXiv:2610.39427 — arXiv (en), https://arxiv.org/abs/2610.39427 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2e2bc9709bd5 (Metraipolis archive dc_2e2bc9709bd5, sha256 dd7abee6838469e5f1544523229f97b9a95dec11e6dc751f460cc0ff7884fa0b)
BibTeX
@misc{dc2e2bc9709bd5,
title = {EmpDPO: Enabling Emphasis Control in TTS via Direct Preference Optimization — arXiv:2610.39427},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.39427},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2e2bc9709bd5; sha256 dd7abee6838469e5f1544523229f97b9a95dec11e6dc751f460cc0ff7884fa0b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39427. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Word-level emphasis conveys meaning that text alone cannot express and is therefore essential for a practical text-to-speech (TTS) system. In this work, we study how to add emphasis control post hoc to a pretrained TTS model that has never been trained with emphasis annotations. We present EmpDPO, a simple, efficient, and effective two-stage recipe that adds emphasis control to a multilingual zero-shot diffusion TTS model through supervised fine-tuning followed by direct preference optimization (DPO). The training signals for both stages come from an off-the-shelf multilingual emphasis detector, so that no manual emphasis annotation or task-specific reward design is needed. We find that DPO can substantially strengthen emphasis control with only a few thousand preference pairs and training steps. Objective and subjective evaluations against strong public systems show that our model produces perceptible emphasis while preserving naturalness and overall quality. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv eess.AS, nuovi lavori del giorno). Categorie arXiv: Sound (cs.SD) ; Audio and Speech Processing (eess.AS). Pagina del lavoro: https://arxiv.org/abs/2610.39427 — 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 2026-11-01T02:26:00.577Z dalla pagina https://arxiv.org/list/eess.AS/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).