An Adaptive Human-in-the-Loop Generative AI Framework for Professional-Supported Pronunciation Exercise Design: Ex Ante Evaluation in Down Syndrome
Big Data and Cognitive Computing · 12.11.2026 · 10 (11) · 387
DOI: 10.3390/bdcc10110387 ↗Kurz gefasst
Fachartikel in der Zeitschrift Big Data and Cognitive Computing, online erschienen am 12.11.2026. Verfasst von Geovanny Cudco und 4 weiteren Autor:innen. Die Arbeit nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Personalized pronunciation-exercise design requires context-sensitive content, longitudinal adaptation, and professional oversight. This study presents Speak4All, a cloud-deployed human-in-the-loop (HITL) generative AI framework integrating structured learner profiles, professional assessments, interpretable difficulty recommendations, deterministic constraint validation, and explicit human control. Following a Design Science Research approach, an ex ante evaluation examined scenarios involving children with Down syndrome without recruiting children as participants. Two complementary settings were considered: an exploratory assessment with eight adult stakeholders (two speech-language professionals and six caregivers) in Ecuador and a remote controlled evaluation involving 25 education professionals and 25 structured cases. Compared with prompt-only and profile-aware generation, the integrated framework achieved higher educator ratings and 84.8% acceptance without editing across exercise-evaluation decisions. All retained exercises satisfied the specified hard constraints (100.0% post-validation compliance). Adaptive recommendations achieved 87.0% exact agreement with independent educator judgments (κw=0.848), with 85.0% accepted without modification. Stakeholder feedback indicated favorable perceptions of personalization, progress monitoring, and multimedia support. These findings support the framework’s ex ante technical feasibility and potential usefulness for professional-supervised educational decision support, without establishing clinical effectiveness. Future research should evaluate supervised use with children through validated speech-related outcome measures.
Zitieren
APA
Cudco, G., Álvarez-Jiménez, M., Pinto, H., Sanlucas-Perez, A. C., & Flores-Ayala, F. (2026). An Adaptive Human-in-the-Loop Generative AI Framework for Professional-Supported Pronunciation Exercise Design: Ex Ante Evaluation in Down Syndrome. Big Data and Cognitive Computing, 10(11), 387. https://doi.org/10.3390/bdcc10110387
Vancouver
Cudco G, Álvarez-Jiménez M, Pinto H, Sanlucas-Perez AC, Flores-Ayala F. An Adaptive Human-in-the-Loop Generative AI Framework for Professional-Supported Pronunciation Exercise Design: Ex Ante Evaluation in Down Syndrome. Big Data and Cognitive Computing. 2026;10(11):387. doi:10.3390/bdcc10110387
BibTeX
@article{Cudco2026,
author = {Cudco, Geovanny and Álvarez-Jiménez, Mayra and Pinto, Hector and Sanlucas-Perez, Ana Cecilia and Flores-Ayala, Franklin},
title = {An Adaptive Human-in-the-Loop Generative AI Framework for Professional-Supported Pronunciation Exercise Design: Ex Ante Evaluation in Down Syndrome},
journal = {Big Data and Cognitive Computing},
year = {2026},
volume = {10},
number = {11},
pages = {387},
doi = {10.3390/bdcc10110387}
}
EUVIMED