Metraipolis › archive › dc_eb787eb07be6

Can Prosodic Style Be Inferred from Text Alone? Evidence from Unsupervised Acoustic Clusters — arXiv:2610.05575

Source: arXiv
Original: https://arxiv.org/abs/2610.05575
License (as archived): CC0-1.0
Archived: 2026-10-06T05:27:00.647Z
SHA-256 of the archived text: f9d79f5d29071716dc5ead571ec8fae9ace40da935d9bb7c5b012e55d89e6770
Stable URL of this page: https://metraipolis.com/documento/dc_eb787eb07be6

How to cite

Can Prosodic Style Be Inferred from Text Alone? Evidence from Unsupervised Acoustic Clusters — arXiv:2610.05575 — arXiv, https://arxiv.org/abs/2610.05575 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eb787eb07be6 (Metraipolis archive dc_eb787eb07be6, sha256 f9d79f5d29071716dc5ead571ec8fae9ace40da935d9bb7c5b012e55d89e6770)

BibTeX

@misc{dceb787eb07be6,
  title = {Can Prosodic Style Be Inferred from Text Alone? Evidence from Unsupervised Acoustic Clusters — arXiv:2610.05575},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.05575},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eb787eb07be6; sha256 f9d79f5d29071716dc5ead571ec8fae9ace40da935d9bb7c5b012e55d89e6770},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05575. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Much of expressive text-to-speech research rests on an untested assumption that written text carries enough information to select an appropriate prosodic style for its delivery. Text-predicted style models improve listener preference, and expressive-appropriateness evaluation presupposes that context constrains style, yet neither measures the assumption itself. This paper tests it as a falsifiable hypothesis against style labels derived from acoustics alone. For each of six speakers in a 1,200-hour conversational corpus, utterances are clustered in the spaces of five speech models, including a prosody-only control, and the cluster of held-out utterances is predicted from twelve text embedding models. Three controls are applied: utterance length is erased from the speech embeddings; accuracy is scored against the majority-class floor of unbalanced clusters rather than uniform chance; and a bag-of-words baseline measures word identity alone. Text predicts the cluster above that floor for all six speakers (+0.111 top-3 accuracy), but bag-of-words achieves three quarters of this. Sentence embeddings add only +0.026, largest for encoders not trained for sentence semantics and reversed by tree-based probes for all others. Acoustic clusters are not compact in text embedding space in any of 360 configurations. The prosody-only space weakens the association for five speakers, but not for the speaker showing it most strongly. Text thus informs these delivery clusters mainly through word choice, whether as a cue to prosody or as a marker of topic and recording situation, and reference-free style selection cannot assume more.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.05575 — 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 2026-10-06T05:24:06.045Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).