Zhang Vicky W, Sebastian Arun, Monaghan Jessica J M
National Acoustic Laboratories, Sydney, NSW 2109, Australia.
Department of Linguistics, Macquarie University, Sydney, NSW 2109, Australia.
J Clin Med. 2025 Jul 25;14(15):5280. doi: 10.3390/jcm14155280.
: Speech intelligibility (SI) is a key indicator of spoken language development, especially for children with hearing loss, as it directly impacts communication and social engagement. However, due to logistical and methodological challenges, SI assessment is often underutilised in clinical practice. This study aimed to evaluate the accuracy and consistency of an artificial intelligence (AI)-based transcription model in assessing SI in young children with cochlear implants (CI), hearing aids (HA), or normal hearing (NH), in comparison to naïve human listeners. : A total of 580 speech samples from 58 five-year-old children were transcribed by three naïve listeners and the AI model. Word-level transcription accuracy was evaluated using Bland-Altman plots, intraclass correlation coefficients (ICCs), and word error rate (WER) metrics. Performance was compared across the CI, HA, and NH groups. : The AI model demonstrated high consistency with naïve listeners across all groups. Bland-Altman analyses revealed minimal bias, with fewer than 6% of sentences falling outside the 95% limits of agreement. ICC values exceeded 0.9 in all groups, with particularly strong agreement in the NH and CI groups (ICCs > 0.95). WER results further confirmed this alignment and indicated that children with CIs showed better SI performance than those using HAs. : The AI-based method offers a reliable and objective solution for SI assessment in young children. Its agreement with human performance supports its integration into clinical and home environments for early intervention and ongoing monitoring of speech development in children with hearing loss.
言语可懂度（SI）是口语语言发展的关键指标，对于听力损失儿童尤为重要，因为它直接影响沟通和社交参与。然而，由于后勤和方法上的挑战，SI评估在临床实践中常常未得到充分利用。本研究旨在评估一种基于人工智能（AI）的转录模型在评估人工耳蜗（CI）、助听器（HA）或听力正常（NH）的幼儿的SI方面的准确性和一致性，并与未经训练的人类听众进行比较。
共有来自58名五岁儿童的580个语音样本由三名未经训练的听众和AI模型进行转录。使用Bland-Altman图、组内相关系数（ICC）和词错误率（WER）指标评估单词级转录准确性。对CI、HA和NH组的表现进行了比较。
AI模型在所有组中与未经训练的听众表现出高度一致性。Bland-Altman分析显示偏差极小，不到6%的句子落在95%一致性界限之外。所有组的ICC值均超过0.9，在NH组和CI组中一致性尤其强（ICC>0.95）。WER结果进一步证实了这种一致性，并表明使用CI的儿童的SI表现优于使用HA的儿童。
基于AI的方法为幼儿的SI评估提供了一种可靠且客观的解决方案。它与人类表现的一致性支持将其整合到临床和家庭环境中，用于对听力损失儿童的言语发展进行早期干预和持续监测。
