@inproceedings{mote-busso-2026-embrace,
title = "{EMBRACE}: Emotion-Based Representation Across Cultures {\&} Expressions",
author = "Mote, Pravin and
Busso, Carlos",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.2174/",
pages = "46509--46520",
ISBN = "979-8-89176-462-0",
abstract = "Building speech emotion recognition (SER) models that generalize across languages remains challenging due to limited annotations, linguistic diversity and heterogeneous label spaces. Current multilingual SER approaches either rely on fully shared models or restrict training to a small set of overlapping emotions that restrict diversity in expressiveness. We propose EMBRACE, a multilingual speech representation for language-agnostic SER. Drawing inspiration from partial-label learning paradigms in computer vision, EMBRACE adapts a unified superset emotion modeling strategy. The approach enables training on mixtures of datasets with non-overlapping emotion categories by selectively masking absent categories during optimization. To balance this complex multi-domain training, the model leverages a knowledge distillation based progressive training procedure that stabilizes multilingual optimization and mitigates catastrophic forgetting. Experiments across seven languages show that EMBRACE improves cross-corpus performance by 31.8{\%} and in-corpus by 15.2{\%} over strong emotional speech representations, confirming its ability to learn discriminative and transferable affective representations."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mote-busso-2026-embrace">
<titleInfo>
<title>EMBRACE: Emotion-Based Representation Across Cultures & Expressions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pravin</namePart>
<namePart type="family">Mote</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carlos</namePart>
<namePart type="family">Busso</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Building speech emotion recognition (SER) models that generalize across languages remains challenging due to limited annotations, linguistic diversity and heterogeneous label spaces. Current multilingual SER approaches either rely on fully shared models or restrict training to a small set of overlapping emotions that restrict diversity in expressiveness. We propose EMBRACE, a multilingual speech representation for language-agnostic SER. Drawing inspiration from partial-label learning paradigms in computer vision, EMBRACE adapts a unified superset emotion modeling strategy. The approach enables training on mixtures of datasets with non-overlapping emotion categories by selectively masking absent categories during optimization. To balance this complex multi-domain training, the model leverages a knowledge distillation based progressive training procedure that stabilizes multilingual optimization and mitigates catastrophic forgetting. Experiments across seven languages show that EMBRACE improves cross-corpus performance by 31.8% and in-corpus by 15.2% over strong emotional speech representations, confirming its ability to learn discriminative and transferable affective representations.</abstract>
<identifier type="citekey">mote-busso-2026-embrace</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.2174/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>46509</start>
<end>46520</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T EMBRACE: Emotion-Based Representation Across Cultures & Expressions
%A Mote, Pravin
%A Busso, Carlos
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F mote-busso-2026-embrace
%X Building speech emotion recognition (SER) models that generalize across languages remains challenging due to limited annotations, linguistic diversity and heterogeneous label spaces. Current multilingual SER approaches either rely on fully shared models or restrict training to a small set of overlapping emotions that restrict diversity in expressiveness. We propose EMBRACE, a multilingual speech representation for language-agnostic SER. Drawing inspiration from partial-label learning paradigms in computer vision, EMBRACE adapts a unified superset emotion modeling strategy. The approach enables training on mixtures of datasets with non-overlapping emotion categories by selectively masking absent categories during optimization. To balance this complex multi-domain training, the model leverages a knowledge distillation based progressive training procedure that stabilizes multilingual optimization and mitigates catastrophic forgetting. Experiments across seven languages show that EMBRACE improves cross-corpus performance by 31.8% and in-corpus by 15.2% over strong emotional speech representations, confirming its ability to learn discriminative and transferable affective representations.
%U https://aclanthology.org/2026.findings-emnlp.2174/
%P 46509-46520
Markdown (Informal)
[EMBRACE: Emotion-Based Representation Across Cultures & Expressions](https://aclanthology.org/2026.findings-emnlp.2174/) (Mote & Busso, Findings 2026)
ACL