Automatic Prediction of Prominence and Boundary Strength from Text

Pauline Mas, Kévin Vythelingum, Jonathan Chevelu, Marion Ouédraogo, Damien Lolive, Olivier Rosec


Abstract
In Text-to-Speech synthesis (TTS), the prediction of prosodic information from text is a difficult challenge, since it requires information related to the context that may not be present in the text. Previous studies have shown that prosodic annotations from an oracle benefit TTS models and improve their prosodic rendering as well as their controllability. In this paper, we investigate different strategies to automatically predict prominence and boundary strength from text. We compare three prediction strategies on a French audiobook dataset: dedicated predictors jointly trained in a TTS model, a BERT-informed Prosody Predictor (BIPP) and its auto-regressive counterpart, both benefiting from semantic text embeddings. BIPP exhibits the best performance in our experiments, indicating that using phonetized syllables as complementary information to the semantic embedding provided by a BERT-like model is the best strategy to predict prosodic events.
Anthology ID:
2026.lrec-1.437
Volume:
Proceedings of the Fifteenth Language Resources and Evaluation Conference
Month:
May
Year:
2026
Address:
Palma de Mallorca, Spain
Editors:
Stelios Piperidis, Núria Bel, Henk van den Heuvel, Nancy Ide, Simon Krek, Antonio Toral
Venue:
LREC
SIG:
Publisher:
ELRA Language Resource Association
Note:
Pages:
5588–5596
Language:
External URL:
https://lrec.elra.info/lrec2026-main-437
DOI:
10.63317/3k3ii2w38tnj
Bibkey:
Cite (ACL):
Pauline Mas, Kévin Vythelingum, Jonathan Chevelu, Marion Ouédraogo, Damien Lolive, and Olivier Rosec. 2026. Automatic Prediction of Prominence and Boundary Strength from Text. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 5588–5596, Palma de Mallorca, Spain. ELRA Language Resource Association.
Cite (Informal):
Automatic Prediction of Prominence and Boundary Strength from Text (Mas et al., LREC 2026)
Copy Citation: