Page 138 - 南京医科大学自然版

南京医科大学学报（自然科学版） 第45卷第4期
·574 · Journal of Nanjing Medical University（Natural Sciences） 2025年4月

·综 述·

语音识别技术在孤独症谱系障碍诊断中的研究进展与应用展望

李进宇，赵太宏 *
南京医科大学附属脑科医院院长办公室，江苏 南京 210024

［摘 要］ 孤独症谱系障碍（autism spectrum disorder，ASD）是一种起病于发育早期的神经发育障碍，其核心症状主要表现在
语言和社会交往方面。传统诊断工具（如《自闭症诊断观察量表第2版》）应用广泛，但在低龄儿童和基层医疗中可及性与客观
性不足。语音识别技术因其量化能力强、成本较低、识别婴幼儿早期言语异常的灵敏度高，正成为辅助诊断 ASD 的重要手
段。文章系统梳理了语音识别技术在不同年龄段早期筛查、共病情绪问题诊断、疾病严重程度评估及多模态融合等方面的最
新研究。结果显示，通过提取基频、语速、停顿等声学特征，可有效区分ASD个体与典型发育儿童，并识别焦虑、抑郁及注意力
缺陷多动障碍等共病。多模态融合（如脑影像、生理信号和行为数据）可进一步提升诊断准确率。但数据多样性不足、方言与
年龄适用性局限、共病干扰及隐私保护等挑战依然突出。
［关键词］ 孤独症谱系障碍；语音识别；辅助诊断
［中图分类号］ TN912.34；R749.94 ［文献标志码］ A ［文章编号］ 1007⁃4368（2025）04⁃574⁃07
doi：10.7655/NYDXBNSN241209

Research progress and application prospects of speech recognition technology in autism
spectrum disorder diagnosis

LI Jinyu，ZHAO Taihong *
Office of the Dean，the Affiliated Brain Hospital of Nanjing Medical University，Nanjing 210024，China

［Abstract］ Autism spectrum disorder（ASD）is a neurodevelopmental disorder that typically emerges in early childhood，with core
symptoms predominantly manifesting in language and social interaction. Although traditional diagnostic tools，such as the Autism
Diagnostic Observation Schedule⁃2，are widely used，they often have limited accessibility and objectivity in younger children and in
primary healthcare settings. Due to its strong quantitative capabilities，relatively low cost，and high sensitivity to early speech
anomalies in infants，speech recognition technology has emerged as a promising approach for ASD diagnostic support. This paper
systematically reviews the latest research on the application of speech recognition in early screening across different age groups，
diagnosis of comorbid emotional issues，assessment of disease severity，and multimodal data integration. The findings indicate that
extracting acoustic features（such as fundamental frequency，speech rate，and pauses）can effectively distinguish individuals with ASD
from typically developing children，while also identifying comorbidities like anxiety，depression，and attention deficit hyperactivity
disorder. Furthermore，multimodal fusion（e.g.，neuroimaging，physiological signals，and behavioral data）can further improve
diagnostic accuracy. However，challenges persist，including inadequate data diversity，limitations related to dialect and age
applicability，confounding effects of comorbid conditions，and concerns over privacy.
［Key words］ autism spectrum disorder；speech recognition；asistant diagnosis
［J Nanjing Med Univ，2025，45（04）：574⁃579，587］

孤 独 症 谱 系 障 碍（autism spectrum disorder，
ASD）是一种起病于发育早期的神经发育障碍，其核
［基金项目］ 南京市卫生科技发展专项资金（ZKX24053）
心表现包括社会交往障碍、语言或沟通能力受损，
∗
通信作者（Corresponding author），E⁃mail：zhaotaihong@njmu.
［1］
edu.cn（ORCID：0009⁃0006⁃4275⁃518X） 以及刻板或重复性行为 。近年来，ASD 的发病率