analiza aiqbench
Paediatric-HGNN addresses a critical gap in automated speech analysis by shifting from standard 1D signal modeling to a heterogeneous graph approach that captures hierarchical interactions between lexical units and acoustic frames. This architecture specifically targets the high variability of developing voices, achieving improved accuracy in distinguishing pathological stuttering from typical disfluencies in children. The method offers a more robust and interpretable foundation for early clinical intervention tools in pediatric speech processing.
Paediatric-HGNN: A Hybrid Heterogeneous Graph Neural Network for Detecting Disfluency in Children's Speech via Multiscale Acoustic Fusion
arXiv:2606.08210v1 Announce Type: 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:2606.08210v1 [eess.AS] for this version)
https://doi.org/10.48550/arXiv.2606.08210 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
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.
Text integral sub licența deschisă a publicației · 211 cuvinte