@inproceedings{bailly-etal-2024-emotags,
title = "Emotags: Computer-Assisted Verbal Labelling of Expressive Audiovisual Utterances for Expressive Multimodal {TTS}",
author = {Bailly, G{\'e}rard and
Legrand, Romain and
Lenglet, Martin and
Elisei, Fr{\'e}d{\'e}ric and
Garnier, Ma{\"e}va and
Perrotin, Olivier},
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.505/",
pages = "5689--5695",
abstract = "We developped a web app for ascribing verbal descriptions to expressive audiovisual utterances. These descriptions are limited to lists of adjectives that are either suggested via a navigation in emotional latent spaces built using discriminant analysis of BERT embeddings or entered freely by subjects. We show that such verbal descriptions collected on-line via Prolific on massive data (310 participants, 12620 labelled utterances up-to-now) provide Expressive Multimodal Text-to-Speech Synthesis with precise verbal control over desired emotional content"
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bailly-etal-2024-emotags">
<titleInfo>
<title>Emotags: Computer-Assisted Verbal Labelling of Expressive Audiovisual Utterances for Expressive Multimodal TTS</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gérard</namePart>
<namePart type="family">Bailly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Romain</namePart>
<namePart type="family">Legrand</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Lenglet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Elisei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maëva</namePart>
<namePart type="family">Garnier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Olivier</namePart>
<namePart type="family">Perrotin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We developped a web app for ascribing verbal descriptions to expressive audiovisual utterances. These descriptions are limited to lists of adjectives that are either suggested via a navigation in emotional latent spaces built using discriminant analysis of BERT embeddings or entered freely by subjects. We show that such verbal descriptions collected on-line via Prolific on massive data (310 participants, 12620 labelled utterances up-to-now) provide Expressive Multimodal Text-to-Speech Synthesis with precise verbal control over desired emotional content</abstract>
<identifier type="citekey">bailly-etal-2024-emotags</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.505/</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>5689</start>
<end>5695</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Emotags: Computer-Assisted Verbal Labelling of Expressive Audiovisual Utterances for Expressive Multimodal TTS
%A Bailly, Gérard
%A Legrand, Romain
%A Lenglet, Martin
%A Elisei, Frédéric
%A Garnier, Maëva
%A Perrotin, Olivier
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F bailly-etal-2024-emotags
%X We developped a web app for ascribing verbal descriptions to expressive audiovisual utterances. These descriptions are limited to lists of adjectives that are either suggested via a navigation in emotional latent spaces built using discriminant analysis of BERT embeddings or entered freely by subjects. We show that such verbal descriptions collected on-line via Prolific on massive data (310 participants, 12620 labelled utterances up-to-now) provide Expressive Multimodal Text-to-Speech Synthesis with precise verbal control over desired emotional content
%U https://aclanthology.org/2024.lrec-main.505/
%P 5689-5695
Markdown (Informal)
[Emotags: Computer-Assisted Verbal Labelling of Expressive Audiovisual Utterances for Expressive Multimodal TTS](https://aclanthology.org/2024.lrec-main.505/) (Bailly et al., LREC-COLING 2024)
ACL