@inproceedings{mas-etal-2026-automatic,
title = "Automatic Prediction of Prominence and Boundary Strength from Text",
author = "Mas, Pauline and
Vythelingum, K{\'e}vin and
Chevelu, Jonathan and
Ou{\'e}draogo, Marion and
Lolive, Damien and
Rosec, Olivier",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.437/",
doi = "10.63317/3k3ii2w38tnj",
pages = "5588--5596",
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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mas-etal-2026-automatic">
<titleInfo>
<title>Automatic Prediction of Prominence and Boundary Strength from Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pauline</namePart>
<namePart type="family">Mas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kévin</namePart>
<namePart type="family">Vythelingum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Chevelu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marion</namePart>
<namePart type="family">Ouédraogo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Damien</namePart>
<namePart type="family">Lolive</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Olivier</namePart>
<namePart type="family">Rosec</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">mas-etal-2026-automatic</identifier>
<identifier type="doi">10.63317/3k3ii2w38tnj</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.437/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>5588</start>
<end>5596</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Prediction of Prominence and Boundary Strength from Text
%A Mas, Pauline
%A Vythelingum, Kévin
%A Chevelu, Jonathan
%A Ouédraogo, Marion
%A Lolive, Damien
%A Rosec, Olivier
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F mas-etal-2026-automatic
%X 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.
%R 10.63317/3k3ii2w38tnj
%U https://aclanthology.org/2026.lrec-1.437/
%U https://doi.org/10.63317/3k3ii2w38tnj
%P 5588-5596
Markdown (Informal)
[Automatic Prediction of Prominence and Boundary Strength from Text](https://aclanthology.org/2026.lrec-1.437/) (Mas et al., LREC 2026)
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.