New AI System Improves Detection of Stuttering and Speech Disfluencies in Children
Researchers have developed Paediatric-HGNN, a hybrid graph neural network designed to automatically detect stuttering and disfluency in children's speech. The system addresses a longstanding challenge in automated stuttering detection: distinguishing pathological stuttering from normal developmental disfluencies in young, acoustically variable voices. The work, accepted at INTERSPEECH 2026, could support earlier and more reliable clinical intervention for children with speech disorders.
A team of researchers has introduced Paediatric-HGNN, a framework built around a Context-aware Part-whole Interaction Network (CaPIN) specifically designed for paediatric speech data. Unlike conventional one-dimensional signal modelling approaches, the system constructs a heterogeneous graph that captures hierarchical relationships between word-level lexical units and fine-grained acoustic frame segments. This multiscale structure allows the model to represent the developmental 'searching' behaviour characteristic of children's speech, which can superficially resemble pathological stuttering. Trained and evaluated on two curated paediatric corpora—UCLASS and FluencyBank—the model achieved 82.4% weighted accuracy and a Typical Disfluency F1-score of 0.386. The authors argue the approach is both more robust and more interpretable than prior methods, making it potentially useful as a clinical screening tool for early intervention in childhood speech disorders.
What's missing
A Typical Disfluency F1-score of 0.386 is relatively low, suggesting the model still struggles to reliably distinguish typical from pathological disfluency—a core clinical requirement. The paper does not report comparison against established clinical baselines or human expert performance, making it difficult to assess real-world clinical readiness. Generalisability across languages, dialects, and recording conditions beyond the two training corpora is also unaddressed.
What different sources said
- arXiv cs.CLCenter
Paediatric-HGNN: A Hybrid Heterogeneous Graph Neural Network for Detecting Disfluency in Children's Speech via Multiscale Acoustic Fusion
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.