Deep Learning-Based Multi-Aspect Pronunciation Assessment for Individuals with Down Syndrome

David Fernández-García, César González-Ferreras, Valentín Cardeñoso-Payo, Mario Corrales-Astorgano


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.
Anthology ID:
2026.lrec-1.667
Volume:
Proceedings of the Fifteenth Language Resources and Evaluation Conference
Month:
May
Year:
2026
Address:
Palma de Mallorca, Spain
Editors:
Stelios Piperidis, Núria Bel, Henk van den Heuvel, Nancy Ide, Simon Krek, Antonio Toral
Venue:
LREC
SIG:
Publisher:
ELRA Language Resource Association
Note:
Pages:
8455–8464
Language:
External URL:
https://lrec.elra.info/lrec2026-main-667
DOI:
10.63317/4g3dwy2kmira
Bibkey:
Cite (ACL):
David Fernández-García, César González-Ferreras, Valentín Cardeñoso-Payo, and Mario Corrales-Astorgano. 2026. Deep Learning-Based Multi-Aspect Pronunciation Assessment for Individuals with Down Syndrome. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 8455–8464, Palma de Mallorca, Spain. ELRA Language Resource Association.
Cite (Informal):
Deep Learning-Based Multi-Aspect Pronunciation Assessment for Individuals with Down Syndrome (Fernández-García et al., LREC 2026)
Copy Citation: