@inproceedings{boll-etal-2026-pretrained,
title = "Pretrained Neural Audio Models for Asthma Detection from Voice and Speech",
author = "Boll, Leticia Puttlitz and
Boll, Antonio Oss and
Oliveira, Yan Anderson Pires de and
Silva, Victor dos Santos and
Pestana, Mariana Lopes and
Carvalho, Celso Ricardo Fernandes de and
Gauy, Marcelo Matheus and
Finger, Marcelo",
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. 2",
month = apr,
year = "2026",
address = "Salvador, Brazil",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.propor-2.13/",
pages = "58--67",
ISBN = "979-8-89176-387-6",
abstract = "Asthma is a chronic respiratory disease that affects breathing and may also influence speech and voice production. In this paper, we examine whether short mobile-recorded Brazilian Portuguese voice and speech audio contain cues that can be used to distinguish individuals with asthma from those without asthma. We approach this problem using transfer learning with pretrained neural audio models based on convolutional architectures trained on large-scale audio datasets (PANNs). We evaluate two recording types: sustained vowel phonation and read speech. Models are trained for a binary classification task and evaluated at both the segment level and the patient level. Read speech performs better than sustained vowels. The best configuration (CNN14 on speech) achieves 0.85 patient-level balanced accuracy (accuracy 0.85) with ROC-AUC 0.93 and PR-AUC 0.98, performing comparably to CNN10. Training from scratch performs worse than fine-tuning a pretrained model, showing that pretraining helps when data is limited. Performance also varies across age groups, suggesting demographic sensitivity. These findings support the feasibility of audio-based asthma classification from voice and speech and motivate further investigation of pretrained audio models in biomedical applications."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="boll-etal-2026-pretrained">
<titleInfo>
<title>Pretrained Neural Audio Models for Asthma Detection from Voice and Speech</title>
</titleInfo>
<name type="personal">
<namePart type="given">Leticia</namePart>
<namePart type="given">Puttlitz</namePart>
<namePart type="family">Boll</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="given">Oss</namePart>
<namePart type="family">Boll</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yan</namePart>
<namePart type="given">Anderson</namePart>
<namePart type="given">Pires</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">Victor</namePart>
<namePart type="given">dos</namePart>
<namePart type="given">Santos</namePart>
<namePart type="family">Silva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mariana</namePart>
<namePart type="given">Lopes</namePart>
<namePart type="family">Pestana</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Celso</namePart>
<namePart type="given">Ricardo</namePart>
<namePart type="given">Fernandes</namePart>
<namePart type="given">de</namePart>
<namePart type="family">Carvalho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcelo</namePart>
<namePart type="given">Matheus</namePart>
<namePart type="family">Gauy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcelo</namePart>
<namePart type="family">Finger</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. 2</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>Asthma is a chronic respiratory disease that affects breathing and may also influence speech and voice production. In this paper, we examine whether short mobile-recorded Brazilian Portuguese voice and speech audio contain cues that can be used to distinguish individuals with asthma from those without asthma. We approach this problem using transfer learning with pretrained neural audio models based on convolutional architectures trained on large-scale audio datasets (PANNs). We evaluate two recording types: sustained vowel phonation and read speech. Models are trained for a binary classification task and evaluated at both the segment level and the patient level. Read speech performs better than sustained vowels. The best configuration (CNN14 on speech) achieves 0.85 patient-level balanced accuracy (accuracy 0.85) with ROC-AUC 0.93 and PR-AUC 0.98, performing comparably to CNN10. Training from scratch performs worse than fine-tuning a pretrained model, showing that pretraining helps when data is limited. Performance also varies across age groups, suggesting demographic sensitivity. These findings support the feasibility of audio-based asthma classification from voice and speech and motivate further investigation of pretrained audio models in biomedical applications.</abstract>
<identifier type="citekey">boll-etal-2026-pretrained</identifier>
<location>
<url>https://aclanthology.org/2026.propor-2.13/</url>
</location>
<part>
<date>2026-04</date>
<extent unit="page">
<start>58</start>
<end>67</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Pretrained Neural Audio Models for Asthma Detection from Voice and Speech
%A Boll, Leticia Puttlitz
%A Boll, Antonio Oss
%A Oliveira, Yan Anderson Pires de
%A Silva, Victor dos Santos
%A Pestana, Mariana Lopes
%A Carvalho, Celso Ricardo Fernandes de
%A Gauy, Marcelo Matheus
%A Finger, Marcelo
%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. 2
%D 2026
%8 April
%I Association for Computational Linguistics
%C Salvador, Brazil
%@ 979-8-89176-387-6
%F boll-etal-2026-pretrained
%X Asthma is a chronic respiratory disease that affects breathing and may also influence speech and voice production. In this paper, we examine whether short mobile-recorded Brazilian Portuguese voice and speech audio contain cues that can be used to distinguish individuals with asthma from those without asthma. We approach this problem using transfer learning with pretrained neural audio models based on convolutional architectures trained on large-scale audio datasets (PANNs). We evaluate two recording types: sustained vowel phonation and read speech. Models are trained for a binary classification task and evaluated at both the segment level and the patient level. Read speech performs better than sustained vowels. The best configuration (CNN14 on speech) achieves 0.85 patient-level balanced accuracy (accuracy 0.85) with ROC-AUC 0.93 and PR-AUC 0.98, performing comparably to CNN10. Training from scratch performs worse than fine-tuning a pretrained model, showing that pretraining helps when data is limited. Performance also varies across age groups, suggesting demographic sensitivity. These findings support the feasibility of audio-based asthma classification from voice and speech and motivate further investigation of pretrained audio models in biomedical applications.
%U https://aclanthology.org/2026.propor-2.13/
%P 58-67
Markdown (Informal)
[Pretrained Neural Audio Models for Asthma Detection from Voice and Speech](https://aclanthology.org/2026.propor-2.13/) (Boll et al., PROPOR 2026)
ACL
- Leticia Puttlitz Boll, Antonio Oss Boll, Yan Anderson Pires de Oliveira, Victor dos Santos Silva, Mariana Lopes Pestana, Celso Ricardo Fernandes de Carvalho, Marcelo Matheus Gauy, and Marcelo Finger. 2026. Pretrained Neural Audio Models for Asthma Detection from Voice and Speech. In Proceedings of the 17th International Conference on Computational Processing of Portuguese (PROPOR 2026) - Vol. 2, pages 58–67, Salvador, Brazil. Association for Computational Linguistics.