@inproceedings{filho-etal-2025-brspeech,
title = "{BRS}peech-{DF}: A Deep Fake Synthetic Speech Dataset for {P}ortuguese Zero-Shot {TTS}",
author = "Filho, Alexandre Costa Ferro and
Virgilli, Rafaello and
Souza, Lucas Alcantara and
de Oliveira, F S and
Ferreira, Marcelo Henrique Lopes and
Tunnermann, Daniel and
Oliveira, Gustavo Dos Reis and
Soares, Anderson Da Silva and
Galv{\~a}o Filho, Arlindo Rodrigues",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.1780/",
pages = "35110--35115",
ISBN = "979-8-89176-332-6",
abstract = "The detection of audio deepfakes (ADD) has become increasingly important due to the rapid evolution of generative speech models. However, progress in this field remains uneven across languages, particularly for low-resource languages like Portuguese, which lack high-quality datasets. In this paper, we introduce BRSpeech-DF, the first publicly available ADD dataset for Portuguese, encompassing both Brazilian and European variants. The dataset contains over 458,000 utterances, including a smaller portion of real speech from 62 speakers and a large collection of synthetic samples generated using multiple zero-shot text-to-speech (TTS) models, each conditioned on the original speaker{'}s voice. By providing this resource, our objective is to support the development of robust, multilingual detection systems, thereby advancing equity in speech forensics and security research. BRSpeech-DF addresses a significant gap in annotated data for underrepresented languages, facilitating more inclusive and generalizable advancements in synthetic speech detection."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="filho-etal-2025-brspeech">
<titleInfo>
<title>BRSpeech-DF: A Deep Fake Synthetic Speech Dataset for Portuguese Zero-Shot TTS</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexandre</namePart>
<namePart type="given">Costa</namePart>
<namePart type="given">Ferro</namePart>
<namePart type="family">Filho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rafaello</namePart>
<namePart type="family">Virgilli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucas</namePart>
<namePart type="given">Alcantara</namePart>
<namePart type="family">Souza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">F</namePart>
<namePart type="given">S</namePart>
<namePart type="family">de Oliveira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcelo</namePart>
<namePart type="given">Henrique</namePart>
<namePart type="given">Lopes</namePart>
<namePart type="family">Ferreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tunnermann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gustavo</namePart>
<namePart type="given">Dos</namePart>
<namePart type="given">Reis</namePart>
<namePart type="family">Oliveira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anderson</namePart>
<namePart type="given">Da</namePart>
<namePart type="given">Silva</namePart>
<namePart type="family">Soares</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arlindo</namePart>
<namePart type="given">Rodrigues</namePart>
<namePart type="family">Galvão Filho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>The detection of audio deepfakes (ADD) has become increasingly important due to the rapid evolution of generative speech models. However, progress in this field remains uneven across languages, particularly for low-resource languages like Portuguese, which lack high-quality datasets. In this paper, we introduce BRSpeech-DF, the first publicly available ADD dataset for Portuguese, encompassing both Brazilian and European variants. The dataset contains over 458,000 utterances, including a smaller portion of real speech from 62 speakers and a large collection of synthetic samples generated using multiple zero-shot text-to-speech (TTS) models, each conditioned on the original speaker’s voice. By providing this resource, our objective is to support the development of robust, multilingual detection systems, thereby advancing equity in speech forensics and security research. BRSpeech-DF addresses a significant gap in annotated data for underrepresented languages, facilitating more inclusive and generalizable advancements in synthetic speech detection.</abstract>
<identifier type="citekey">filho-etal-2025-brspeech</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.1780/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>35110</start>
<end>35115</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BRSpeech-DF: A Deep Fake Synthetic Speech Dataset for Portuguese Zero-Shot TTS
%A Filho, Alexandre Costa Ferro
%A Virgilli, Rafaello
%A Souza, Lucas Alcantara
%A de Oliveira, F. S.
%A Ferreira, Marcelo Henrique Lopes
%A Tunnermann, Daniel
%A Oliveira, Gustavo Dos Reis
%A Soares, Anderson Da Silva
%A Galvão Filho, Arlindo Rodrigues
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F filho-etal-2025-brspeech
%X The detection of audio deepfakes (ADD) has become increasingly important due to the rapid evolution of generative speech models. However, progress in this field remains uneven across languages, particularly for low-resource languages like Portuguese, which lack high-quality datasets. In this paper, we introduce BRSpeech-DF, the first publicly available ADD dataset for Portuguese, encompassing both Brazilian and European variants. The dataset contains over 458,000 utterances, including a smaller portion of real speech from 62 speakers and a large collection of synthetic samples generated using multiple zero-shot text-to-speech (TTS) models, each conditioned on the original speaker’s voice. By providing this resource, our objective is to support the development of robust, multilingual detection systems, thereby advancing equity in speech forensics and security research. BRSpeech-DF addresses a significant gap in annotated data for underrepresented languages, facilitating more inclusive and generalizable advancements in synthetic speech detection.
%U https://aclanthology.org/2025.emnlp-main.1780/
%P 35110-35115
Markdown (Informal)
[BRSpeech-DF: A Deep Fake Synthetic Speech Dataset for Portuguese Zero-Shot TTS](https://aclanthology.org/2025.emnlp-main.1780/) (Filho et al., EMNLP 2025)
ACL
- Alexandre Costa Ferro Filho, Rafaello Virgilli, Lucas Alcantara Souza, F S de Oliveira, Marcelo Henrique Lopes Ferreira, Daniel Tunnermann, Gustavo Dos Reis Oliveira, Anderson Da Silva Soares, and Arlindo Rodrigues Galvão Filho. 2025. BRSpeech-DF: A Deep Fake Synthetic Speech Dataset for Portuguese Zero-Shot TTS. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 35110–35115, Suzhou, China. Association for Computational Linguistics.