aiqbench analysis
This paper applies a heterogeneous graph neural network to detect stuttering in children's speech, modelling word-level and frame-level acoustic nodes instead of raw 1D signals. The headline accuracy is 82.4%, but the Typical Disfluency F1 of 0.386 suggests the model struggles with the hardest distinction the authors highlight, and the evaluation rests on curated corpora (UCLASS, FluencyBank). Claims about interpretability and clinical utility are not yet tested against clinicians or real-world screening, so readers should treat them as hypotheses.
Paediatric-HGNN: A Hybrid Heterogeneous Graph Neural Network for Detecting Disfluency in Children's Speech via Multiscale Acoustic Fusion
arXiv:2606.08210v2 Announce Type: replace-cross Abstract: Automated stuttering detection (ASD) systems struggle with paediatric speech due to high acoustic variability in developing voices and the subtle distinction between pathological stuttering and typical developmental disfluencies. We introduce Paediatric-HGNN, a framework using a Context-aware Part-whole Interaction Network (CaPIN) tailored for paediatric data. Instead of conventional 1D signal modelling, our approach builds a heterogeneous graph capturing hierarchical relationships between lexical units (word nodes) and fine-grained acoustic segments (frame nodes). Trained on curated paediatric corpora (UCLASS and FluencyBank), Paediatric-HGNN achieves 82.4% weighted accuracy and a Typical Disfluency F1-score of 0.386. Modelling hierarchical lexical-acoustic interactions captures developmental "searching" behaviour, offering a more robust and interpretable tool for early clinical intervention.
Abstract:Automated stuttering detection (ASD) systems struggle with paediatric speech due to high acoustic variability in developing voices and the subtle distinction between pathological stuttering and typical developmental disfluencies. We introduce Paediatric-HGNN, a framework using a Context-aware Part-whole Interaction Network (CaPIN) tailored for paediatric data. Instead of conventional 1D signal modelling, our approach builds a heterogeneous graph capturing hierarchical relationships between lexical units (word nodes) and fine-grained acoustic segments (frame nodes). Trained on curated paediatric corpora (UCLASS and FluencyBank), Paediatric-HGNN achieves 82.4% weighted accuracy and a Typical Disfluency F1-score of 0.386. Modelling hierarchical lexical-acoustic interactions captures developmental "searching" behaviour, offering a more robust and interpretable tool for early clinical intervention.
Audio and Speech Processing (eess.AS); Computation and Language (cs.CL); Sound (cs.SD)
arXiv:2606.08210 [eess.AS]
(or arXiv:2606.08210v2 [eess.AS] for this version)
https://doi.org/10.48550/arXiv.2606.08210 Focus to learn more arXiv-issued DOI via DataCite
https://doi.org/10.21437/Interspeech.2026-1131 Focus to learn more DOI(s) linking to related resources
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 219 words