Metraipolis › archive › dc_aac412db8a24
Edit Who Speaks, Control How They Speak: Global Timbre Editing and Local Instruction Control for TTS — arXiv:2610.11437
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.11437
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T07:14:06.857Z
- SHA-256 of the archived text
6cdb520ef963bfafb798a30b8ca7203f79487c82098362c864dd957f65478440- Stable URL of this page
https://metraipolis.com/documento/dc_aac412db8a24
How to cite
Edit Who Speaks, Control How They Speak: Global Timbre Editing and Local Instruction Control for TTS — arXiv:2610.11437 — arXiv (en), https://arxiv.org/abs/2610.11437 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_aac412db8a24 (Metraipolis archive dc_aac412db8a24, sha256 6cdb520ef963bfafb798a30b8ca7203f79487c82098362c864dd957f65478440)
BibTeX
@misc{dcaac412db8a24,
title = {Edit Who Speaks, Control How They Speak: Global Timbre Editing and Local Instruction Control for TTS — arXiv:2610.11437},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.11437},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_aac412db8a24; sha256 6cdb520ef963bfafb798a30b8ca7203f79487c82098362c864dd957f65478440},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11437. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Instruction-based text-to-speech (TTS) offers control over voice characteristics and speech expression through interfaces including voice cloning and text-based voice design. Voice cloning reproduces a reference voice, whereas text-based voice design creates a voice from a natural-language description. However, neither interface directly enables users to modify the timbre of a given reference and synthesize speech with the modified voice. Meanwhile, utterance-level expressive instructions leave changes across individual text segments underspecified. We introduce \textbf{EDICT}, a framework that unifies global timbre editing and local expressive control by using an edited acoustic reference to anchor voice identity across segments. To enable synthesis with an instruction-edited voice, EDICT combines reference audio with structured timbre edits to generate an edited reference in codec-token space. This representation serves as a shared voice anchor for a frozen TTS backbone, allowing segment-specific natural-language instructions to guide expression. To accommodate instruction changes while supporting acoustic continuity, EDICT rebuilds the KV cache at each segment boundary, refreshing instruction conditioning while retaining bounded acoustic context from previously generated speech. Evaluations on our proposed TimbreEdit-Bench and IntraTTS-Bench demonstrate improved timbre editing and a favorable balance between local instruction adherence, speaker consistency, and transition quality. Audio demos are available.
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/2610.11437 — 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 2026-10-09T07:08:27.917Z dalla pagina https://arxiv.org/list/eess.AS/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).