arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.03350q-bio.QMcs.LGcs.SDeess.AS
收藏

利用深度学习和超声波自动测量语音期间的颏下肌厚度

Automated Measurement of Geniohyoid Muscle Thickness During Speech Using Deep Learning and Ultrasound

Biomedical Engineering Department, Hong Kong Polytechnic University, Hong Kong, China（生物医学工程系，香港理工大学，香港，中国）；English and Communication Department, Hong Kong Polytechnic University, Hong Kong, China（英语与交流系，香港理工大学，香港，中国）；Department of Language Science and Technology, Hong Kong Polytechnic University, Hong Kong, China（语言科学与技术系，香港理工大学，香港，中国）；Research Institute for Smart Ageing, Hong Kong Polytechnic University, Hong Kong, China（智能老龄化研究学院，香港理工大学，香港，中国）

Alisher Myrgyyassov, Bruce Xiao Wang, Yu Sun, Shuming Huang, Zhen Song, Min Ney Wong, Yongping Zheng

备注：
6 pages, including references and acknowledgements. Submitted to Interspeech 2026
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出SMMA框架，利用深度学习和超声波自动测量语音期间颏下肌厚度，揭示元音发音时的肌肉激活差异及性别影响，为语音运动控制研究提供新方法。

摘要：

在语音期间从超声波中手动测量肌肉形态是耗时的，并限制了大规模研究。我们提出了SMMA，一个完全自动的框架，结合深度学习分割与基于骨架的厚度量化来分析颏下肌（GH）动态。验证显示接近人类水平的准确性（Dice = 0.9037，MAE = 0.53 mm，r = 0.901）。应用于粤语元音生产（N = 11）揭示了系统性模式：/a:/的GH厚度显著大于/i:/（7.29 mm vs 5.95 mm，p < 0.001，Cohen's d > 1.3），表明在生产/a:/时GH激活程度更高，与其在下颌下压中的作用一致。性别差异（男性大5-8%）反映了解剖学缩放。SMMA在无需手动标注的情况下实现了专家验证的准确性，使大规模研究语音运动控制和客观评估语音和吞咽障碍成为可能。

英文摘要：

Manual measurement of muscle morphology from ultrasound during speech is time-consuming and limits large-scale studies. We present SMMA, a fully automated framework that combines deep-learning segmentation with skeleton-based thickness quantification to analyze geniohyoid (GH) muscle dynamics. Validation demonstrates near-human-level accuracy (Dice = 0.9037, MAE = 0.53 mm, r = 0.901). Application to Cantonese vowel production (N = 11) reveals systematic patterns: /a:/ shows significantly greater GH thickness (7.29 mm) than /i:/ (5.95 mm, p < 0.001, Cohen's d > 1.3), suggesting greater GH activation during production of /a:/ than /i:/, consistent with its role in mandibular depression. Sex differences (5-8% greater in males) reflect anatomical scaling. SMMA achieves expert-validated accuracy while eliminating the need for manual annotation, enabling scalable investigations of speech motor control and objective assessment of speech and swallowing disorders.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑