Speech-Based Dysarthria Severity Classification in Amyotrophic Lateral Sclerosis: A Controlled Deep Learning Benchmark
Electronics · 17.11.2026 · 15 (22) · 5362
DOI: 10.3390/electronics15225362 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 17.11.2026. Verfasst von Attaphongse Taparugssanagorn und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Telecommunications Standards Institute.
Abstract (Originalsprache)
This study examines whether adding waveform-derived information-theoretic descriptors to Mel-spectrogram inputs offers a measurable benefit for five-class amyotrophic lateral sclerosis (ALS) dysarthria speech-status classification. The primary evidence is a study-specific, five-fold recording-level CNN comparison: Mel-only accuracy is 0.926±0.012, while historical fusion accuracy is 0.927±0.008. A distinct CNN fusion verification/reproduction run, with traced propagation of the Mel input and all 17 information-theoretic descriptors, reports accuracy of 0.927±0.010; it does not retrospectively verify the archived historical input tensors. Thus, the available comparisons show only a small numerical change, not a demonstrated general advantage of fusion. Complementary analyses include a direct participant-disjoint CNN comparison, a fixed-duration CNN comparison, and seed, duration, padding, and task-specific controls. In the participant-disjoint comparison, Mel-only and fusion achieve accuracies of 0.820 and 0.823, respectively, whereas under the fixed-duration condition they achieve 0.914 and 0.915. These distinct result series show similarly small numerical differences between Mel-only and fusion under the additional evaluation conditions. They do not establish a matched estimate of the effect of participant overlap or a statistically reliable advantage of feature fusion. Source-code auditing identifies discrepancies between an available implementation and the documented score-producing benchmark, without establishing that leakage occurred in the latter. Missing run-linked records, class imbalance, and the absence of external validation constrain conclusions to the evaluated speech-processing pipelines. Class 4 represents ALS without dysarthria, not early bulbar disease detection.
Förderung
- European Telecommunications Standards Institute
Zitieren
APA
Taparugssanagorn, A., Caputo, S., Borghini, G., & Mucchi, L. (2026). Speech-Based Dysarthria Severity Classification in Amyotrophic Lateral Sclerosis: A Controlled Deep Learning Benchmark. Electronics, 15(22), 5362. https://doi.org/10.3390/electronics15225362
Vancouver
Taparugssanagorn A, Caputo S, Borghini G, Mucchi L. Speech-Based Dysarthria Severity Classification in Amyotrophic Lateral Sclerosis: A Controlled Deep Learning Benchmark. Electronics. 2026;15(22):5362. doi:10.3390/electronics15225362
BibTeX
@article{Taparugssanagorn2026,
author = {Taparugssanagorn, Attaphongse and Caputo, Stefano and Borghini, Giacomo and Mucchi, Lorenzo},
title = {Speech-Based Dysarthria Severity Classification in Amyotrophic Lateral Sclerosis: A Controlled Deep Learning Benchmark},
journal = {Electronics},
year = {2026},
volume = {15},
number = {22},
pages = {5362},
doi = {10.3390/electronics15225362}
}
EUVIMED