@inproceedings{matos-etal-2026-contrastive,
title = "Contrastive and Adversarial Disentanglement for Speaker Representations in {B}razilian {P}ortuguese",
author = "Matos, Ariadne Nascimento and
Junior, Arnaldo Candido and
Ponti, Moacir Antonelli",
editor = "Souza, Marlo and
de-Dios-Flores, Iria and
Santos, Diana and
Freitas, Larissa and
Souza, Jackson Wilke da Cruz and
Ribeiro, Eug{\'e}nio",
booktitle = "Proceedings of the 17th International Conference on Computational Processing of {P}ortuguese ({PROPOR} 2026) - Vol. 1",
month = apr,
year = "2026",
address = "Salvador, Brazil",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.propor-1.58/",
pages = "591--600",
ISBN = "979-8-89176-387-6",
abstract = "In this work, we study disentanglement between speaker and environment by combining an adversarial framework with contrastive learning objectives. We investigate supervised contrastive learning (SupCon), which exploits environment labels to structure the environment subspace, and self-supervised SimCLR, which learns invariance from augmented views. Experiments on a controlled synthetic dataset (ST1) and a more realistic corpus (CML-TTS) show that SupCon yields the most discriminative and stable speaker embeddings on ST1, achieving the best verification performance (EER=4.70{\%}, MinDCF=0.24). Overall, our findings emphasize (i) the importance of synthetic benchmarks for diagnosing disentanglement under controlled factor variation and (ii) the effectiveness of combining contrastive and adversarial objectives to encourage speaker representations that are both discriminative and less sensitive to environmental factors."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="matos-etal-2026-contrastive">
<titleInfo>
<title>Contrastive and Adversarial Disentanglement for Speaker Representations in Brazilian Portuguese</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ariadne</namePart>
<namePart type="given">Nascimento</namePart>
<namePart type="family">Matos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arnaldo</namePart>
<namePart type="given">Candido</namePart>
<namePart type="family">Junior</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Moacir</namePart>
<namePart type="given">Antonelli</namePart>
<namePart type="family">Ponti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th International Conference on Computational Processing of Portuguese (PROPOR 2026) - Vol. 1</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marlo</namePart>
<namePart type="family">Souza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iria</namePart>
<namePart type="family">de-Dios-Flores</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diana</namePart>
<namePart type="family">Santos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Larissa</namePart>
<namePart type="family">Freitas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jackson</namePart>
<namePart type="given">Wilke</namePart>
<namePart type="given">da</namePart>
<namePart type="given">Cruz</namePart>
<namePart type="family">Souza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eugénio</namePart>
<namePart type="family">Ribeiro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Salvador, Brazil</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-387-6</identifier>
</relatedItem>
<abstract>In this work, we study disentanglement between speaker and environment by combining an adversarial framework with contrastive learning objectives. We investigate supervised contrastive learning (SupCon), which exploits environment labels to structure the environment subspace, and self-supervised SimCLR, which learns invariance from augmented views. Experiments on a controlled synthetic dataset (ST1) and a more realistic corpus (CML-TTS) show that SupCon yields the most discriminative and stable speaker embeddings on ST1, achieving the best verification performance (EER=4.70%, MinDCF=0.24). Overall, our findings emphasize (i) the importance of synthetic benchmarks for diagnosing disentanglement under controlled factor variation and (ii) the effectiveness of combining contrastive and adversarial objectives to encourage speaker representations that are both discriminative and less sensitive to environmental factors.</abstract>
<identifier type="citekey">matos-etal-2026-contrastive</identifier>
<location>
<url>https://aclanthology.org/2026.propor-1.58/</url>
</location>
<part>
<date>2026-04</date>
<extent unit="page">
<start>591</start>
<end>600</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Contrastive and Adversarial Disentanglement for Speaker Representations in Brazilian Portuguese
%A Matos, Ariadne Nascimento
%A Junior, Arnaldo Candido
%A Ponti, Moacir Antonelli
%Y Souza, Marlo
%Y de-Dios-Flores, Iria
%Y Santos, Diana
%Y Freitas, Larissa
%Y Souza, Jackson Wilke da Cruz
%Y Ribeiro, Eugénio
%S Proceedings of the 17th International Conference on Computational Processing of Portuguese (PROPOR 2026) - Vol. 1
%D 2026
%8 April
%I Association for Computational Linguistics
%C Salvador, Brazil
%@ 979-8-89176-387-6
%F matos-etal-2026-contrastive
%X In this work, we study disentanglement between speaker and environment by combining an adversarial framework with contrastive learning objectives. We investigate supervised contrastive learning (SupCon), which exploits environment labels to structure the environment subspace, and self-supervised SimCLR, which learns invariance from augmented views. Experiments on a controlled synthetic dataset (ST1) and a more realistic corpus (CML-TTS) show that SupCon yields the most discriminative and stable speaker embeddings on ST1, achieving the best verification performance (EER=4.70%, MinDCF=0.24). Overall, our findings emphasize (i) the importance of synthetic benchmarks for diagnosing disentanglement under controlled factor variation and (ii) the effectiveness of combining contrastive and adversarial objectives to encourage speaker representations that are both discriminative and less sensitive to environmental factors.
%U https://aclanthology.org/2026.propor-1.58/
%P 591-600
Markdown (Informal)
[Contrastive and Adversarial Disentanglement for Speaker Representations in Brazilian Portuguese](https://aclanthology.org/2026.propor-1.58/) (Matos et al., PROPOR 2026)
ACL