arXiv cs.CL· Rashini Liyanarachchi, Rachael Mackay, Alison Short, Aditya Joshi, Erik Meijering·· 12 小时前AI 评分20
Paediatric-HGNN：融合多尺度声学特征的混合异构图神经网络，用于儿童言语不流畅检测
Paediatric-HGNN: A Hybrid Heterogeneous Graph Neural Network for Detecting Disfluency in Children's Speech via Multiscale Acoustic Fusion
AI 导读
Paediatric-HGNN 框架通过上下文感知的部分-整体交互网络（CaPIN）构建词节点与帧节点之间的异构图，用于儿童口吃检测，在 UCLASS 和 FluencyBank 数据集上达到 82.4% 加权准确率和 0.386 的典型不流畅 F1 分数。该方法以分层词汇-声学交互建模替代传统 1D 信号建模，可捕捉儿童发育期的"搜索"行为，为早期临床干预提供更稳健、可解释的工具。
正文 · 原文
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.
| Comments: | Proceedings of Interspeech 2026 |
| Subjects: | Audio and Speech Processing (eess.AS); Computation and Language (cs.CL); Sound (cs.SD) |
| Cite as: | arXiv:2606.08210 [eess.AS] |
| (or arXiv:2606.08210v2 [eess.AS] for this version) | |
| https://doi.org/10.48550/arXiv.2606.08210 arXiv-issued DOI via DataCite |
|
| Related DOI: | https://doi.org/10.21437/Interspeech.2026-1131
DOI(s) linking to related resources |
Submission history
From: Rashini Liyanarachchi [view email]
[v1]
Sat, 6 Jun 2026 14:54:44 UTC (296 KB)
[v2]
Sat, 31 Oct 2026 00:16:32 UTC (296 KB)
来源：arXiv cs.CL · arxiv.org