@inproceedings{fernandez-garcia-etal-2026-deep,
title = "Deep Learning-Based Multi-Aspect Pronunciation Assessment for Individuals with Down Syndrome",
author = "Fern{\'a}ndez-Garc{\'i}a, David and
Gonz{\'a}lez-Ferreras, C{\'e}sar and
Carde{\~n}oso-Payo, Valent{\'i}n and
Corrales-Astorgano, Mario",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.667/",
doi = "10.63317/4g3dwy2kmira",
pages = "8455--8464",
abstract = "This paper explores the use of an annotated speech corpus to assess multiple dimensions of speech quality{---}particularly phonetic, fluency and prosody{---}in individuals with Down syndrome, with the aim of informing the development of automated assessment tools. We conducted a series of experiments using the GOPT model, together with representations extracted from fine-tuning Wav2Vec models focused on phoneme classification. Model predictions were compared against expert annotations from a speech-language pathologist using Pearson correlation. Results demonstrate significant improvements over prior work, with correlations up to 0.49 in certain aspects, particularly for phonetic and fluency dimensions, while prosody remained more challenging to model. The study highlights the potential of Transformer-based architectures for atypical speech assessment and underscores the challenges inherent in assessing atypical speech, particularly due to variability linked to specific disfluency types."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fernandez-garcia-etal-2026-deep">
<titleInfo>
<title>Deep Learning-Based Multi-Aspect Pronunciation Assessment for Individuals with Down Syndrome</title>
</titleInfo>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Fernández-García</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">César</namePart>
<namePart type="family">González-Ferreras</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valentín</namePart>
<namePart type="family">Cardeñoso-Payo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mario</namePart>
<namePart type="family">Corrales-Astorgano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper explores the use of an annotated speech corpus to assess multiple dimensions of speech quality—particularly phonetic, fluency and prosody—in individuals with Down syndrome, with the aim of informing the development of automated assessment tools. We conducted a series of experiments using the GOPT model, together with representations extracted from fine-tuning Wav2Vec models focused on phoneme classification. Model predictions were compared against expert annotations from a speech-language pathologist using Pearson correlation. Results demonstrate significant improvements over prior work, with correlations up to 0.49 in certain aspects, particularly for phonetic and fluency dimensions, while prosody remained more challenging to model. The study highlights the potential of Transformer-based architectures for atypical speech assessment and underscores the challenges inherent in assessing atypical speech, particularly due to variability linked to specific disfluency types.</abstract>
<identifier type="citekey">fernandez-garcia-etal-2026-deep</identifier>
<identifier type="doi">10.63317/4g3dwy2kmira</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.667/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>8455</start>
<end>8464</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Deep Learning-Based Multi-Aspect Pronunciation Assessment for Individuals with Down Syndrome
%A Fernández-García, David
%A González-Ferreras, César
%A Cardeñoso-Payo, Valentín
%A Corrales-Astorgano, Mario
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F fernandez-garcia-etal-2026-deep
%X This paper explores the use of an annotated speech corpus to assess multiple dimensions of speech quality—particularly phonetic, fluency and prosody—in individuals with Down syndrome, with the aim of informing the development of automated assessment tools. We conducted a series of experiments using the GOPT model, together with representations extracted from fine-tuning Wav2Vec models focused on phoneme classification. Model predictions were compared against expert annotations from a speech-language pathologist using Pearson correlation. Results demonstrate significant improvements over prior work, with correlations up to 0.49 in certain aspects, particularly for phonetic and fluency dimensions, while prosody remained more challenging to model. The study highlights the potential of Transformer-based architectures for atypical speech assessment and underscores the challenges inherent in assessing atypical speech, particularly due to variability linked to specific disfluency types.
%R 10.63317/4g3dwy2kmira
%U https://aclanthology.org/2026.lrec-1.667/
%U https://doi.org/10.63317/4g3dwy2kmira
%P 8455-8464
Markdown (Informal)
[Deep Learning-Based Multi-Aspect Pronunciation Assessment for Individuals with Down Syndrome](https://aclanthology.org/2026.lrec-1.667/) (Fernández-García et al., LREC 2026)
ACL