@inproceedings{silva-etal-2026-combining,
title = "Combining Real and Synthetic Speech for {ASR} Adaptation in {B}razilian {P}ortuguese",
author = "Silva, Daniel R. da and
Borba, Maria Eduarda S. and
Silva, {\'A}llan C. P. and
Barreto, Maria Carolina S. and
Morais, Arthur F. de and
Santos, Paulo V. dos and
Dutra, Guilherme C. and
Oliveira, S{\'a}vio S. T. de and
Soares, Anderson da S.",
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-1.83/",
pages = "838--846",
ISBN = "979-8-89176-387-6",
abstract = "Automatic Speech Recognition (ASR) systems require large amounts of annotated speech, which are difficult to obtain in specialized domains. This paper introduces GARAGEM: General Automotive Real and Artificial speech corpus for Garage Environments and Maintenance in brazilian portuguese, a domain specific ASR dataset for Brazilian Portuguese focused on automotive repair, combining real speech collected from online sources with synthetic speech generated from curated technical terminology. A reproducible methodology is proposed, encompassing real data acquisition, domain guided synthetic data generation, dataset consolidation, and ASR model fine-tuning. Experiments conducted with the Whisper, Wav2vec 2.0, and Conformer models show that synthetic data provides improvements when used to complement real recordings. Quantitative and qualitative analyses show reductions in Word Error Rate (WER) and Character Error Rate (CER) and improved recognition of domain specific terms absent from the real training set. The results indicate that domain guided synthetic speech is an effective data augmentation strategy for ASR adaptation in specialized and low resource scenarios."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="silva-etal-2026-combining">
<titleInfo>
<title>Combining Real and Synthetic Speech for ASR Adaptation in Brazilian Portuguese</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="given">R</namePart>
<namePart type="given">da</namePart>
<namePart type="family">Silva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">Eduarda</namePart>
<namePart type="given">S</namePart>
<namePart type="family">Borba</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Állan</namePart>
<namePart type="given">C</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Silva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">Carolina</namePart>
<namePart type="given">S</namePart>
<namePart type="family">Barreto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arthur</namePart>
<namePart type="given">F</namePart>
<namePart type="given">de</namePart>
<namePart type="family">Morais</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paulo</namePart>
<namePart type="given">V</namePart>
<namePart type="given">dos</namePart>
<namePart type="family">Santos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guilherme</namePart>
<namePart type="given">C</namePart>
<namePart type="family">Dutra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sávio</namePart>
<namePart type="given">S</namePart>
<namePart type="given">T</namePart>
<namePart type="given">de</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">S</namePart>
<namePart type="family">Soares</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>Automatic Speech Recognition (ASR) systems require large amounts of annotated speech, which are difficult to obtain in specialized domains. This paper introduces GARAGEM: General Automotive Real and Artificial speech corpus for Garage Environments and Maintenance in brazilian portuguese, a domain specific ASR dataset for Brazilian Portuguese focused on automotive repair, combining real speech collected from online sources with synthetic speech generated from curated technical terminology. A reproducible methodology is proposed, encompassing real data acquisition, domain guided synthetic data generation, dataset consolidation, and ASR model fine-tuning. Experiments conducted with the Whisper, Wav2vec 2.0, and Conformer models show that synthetic data provides improvements when used to complement real recordings. Quantitative and qualitative analyses show reductions in Word Error Rate (WER) and Character Error Rate (CER) and improved recognition of domain specific terms absent from the real training set. The results indicate that domain guided synthetic speech is an effective data augmentation strategy for ASR adaptation in specialized and low resource scenarios.</abstract>
<identifier type="citekey">silva-etal-2026-combining</identifier>
<location>
<url>https://aclanthology.org/2026.propor-1.83/</url>
</location>
<part>
<date>2026-04</date>
<extent unit="page">
<start>838</start>
<end>846</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Combining Real and Synthetic Speech for ASR Adaptation in Brazilian Portuguese
%A Silva, Daniel R. da
%A Borba, Maria Eduarda S.
%A Silva, Állan C. P.
%A Barreto, Maria Carolina S.
%A Morais, Arthur F. de
%A Santos, Paulo V. dos
%A Dutra, Guilherme C.
%A Oliveira, Sávio S. T. de
%A Soares, Anderson da S.
%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 silva-etal-2026-combining
%X Automatic Speech Recognition (ASR) systems require large amounts of annotated speech, which are difficult to obtain in specialized domains. This paper introduces GARAGEM: General Automotive Real and Artificial speech corpus for Garage Environments and Maintenance in brazilian portuguese, a domain specific ASR dataset for Brazilian Portuguese focused on automotive repair, combining real speech collected from online sources with synthetic speech generated from curated technical terminology. A reproducible methodology is proposed, encompassing real data acquisition, domain guided synthetic data generation, dataset consolidation, and ASR model fine-tuning. Experiments conducted with the Whisper, Wav2vec 2.0, and Conformer models show that synthetic data provides improvements when used to complement real recordings. Quantitative and qualitative analyses show reductions in Word Error Rate (WER) and Character Error Rate (CER) and improved recognition of domain specific terms absent from the real training set. The results indicate that domain guided synthetic speech is an effective data augmentation strategy for ASR adaptation in specialized and low resource scenarios.
%U https://aclanthology.org/2026.propor-1.83/
%P 838-846
Markdown (Informal)
[Combining Real and Synthetic Speech for ASR Adaptation in Brazilian Portuguese](https://aclanthology.org/2026.propor-1.83/) (Silva et al., PROPOR 2026)
ACL
- Daniel R. da Silva, Maria Eduarda S. Borba, Állan C. P. Silva, Maria Carolina S. Barreto, Arthur F. de Morais, Paulo V. dos Santos, Guilherme C. Dutra, Sávio S. T. de Oliveira, and Anderson da S. Soares. 2026. Combining Real and Synthetic Speech for ASR Adaptation in Brazilian Portuguese. In Proceedings of the 17th International Conference on Computational Processing of Portuguese (PROPOR 2026) - Vol. 1, pages 838–846, Salvador, Brazil. Association for Computational Linguistics.