人工智能技术在听觉言语康复中的应用

蒋春; 薛静; 赵倩; 李瑶; 张艳玲; 孙静; 于丽玫; 邢亚静

doi:1672-4933（2026）03-0267-05

您当前的位置：

首页 >

文章列表页 >

人工智能技术在听觉言语康复中的应用

听障口语者康复现状研究 | 更新时间：2026-05-25

- 人工智能技术在听觉言语康复中的应用
- Applications of Artificial Intelligence in Auditory and Speech Rehabilitation
- 中国听力语言康复科学杂志 2026年24卷第3期页码：241-244
- 作者机构：
  
  中国听力语言康复科学杂志社北京 100029
- 作者简介：
  
  蒋春博士；研究方向：神经生物学
  于丽玫，E-mail：limeiyu@vip.sina.com.
- 基金信息：
  
  2024年中国残联课题“人工智能声音修复技术在听障人士病理腔调中的修复”(2024CDPFHS-10)
- DOI：1672-4933（2026）03-0267-05
  中图分类号： R494
- 收稿：2026-03-25，
  
  纸质出版：2026-05-15
- 稿件说明：
移动端阅览
蒋春,薛静,赵倩等.人工智能技术在听觉言语康复中的应用[J].中国听力语言康复科学杂志,2026,24(03):241-244.

JIANG Chun,XUE Jing,ZHAO Qian,et al.Applications of Artificial Intelligence in Auditory and Speech Rehabilitation[J].Chinese Scientific Journal of Hearing and Speech Rehabilitation,2026,24(03):241-244.
蒋春,薛静,赵倩等.人工智能技术在听觉言语康复中的应用[J].中国听力语言康复科学杂志,2026,24(03):241-244. DOI： 1672-4933（2026）03-0267-05.

JIANG Chun,XUE Jing,ZHAO Qian,et al.Applications of Artificial Intelligence in Auditory and Speech Rehabilitation[J].Chinese Scientific Journal of Hearing and Speech Rehabilitation,2026,24(03):241-244. DOI： 1672-4933（2026）03-0267-05.

摘要

听障人群听觉言语康复面临康复资源分布不均、康复费用高昂等问题，这种现状制约了其对高质量康复需求的发展，尤其是传统的康复手段不能满足成人听障者对听觉言语的康复需求。人工智能（artificial intelligence ，AI）技术为解决该困境提供了新方法。本文总结了AI在此领域的技术演进，从传统信号处理、机器学习、深度学习到大模型与临床转化阶段，介绍了其核心技术架构中的前端感知、中间处理及后端应用。目前AI在语音增强、效果预测、多模态融合及个性化康复方案生成等方面取得显著进展，但仍有数据稀缺与异质性、模型泛化能力不足、临床可解释性差及转化障碍等问题。未来需加强大规模多模态数据库建设，提高模型的分布与泛化能力，促进AI工具与临床的融合，以实现听障人群听觉言语康复的个性化、智能化。

Abstract

Auditory and speech rehabilitation for hearing-impaired population. faces challenges such as uneven distribution of rehabilitation resources and high costs

which constrain the development of high-quality rehabilitation services. In particular

traditional rehabilitation methods fail to meet the auditory and speech rehabilitation needs of adults with hearing loss. The emergence of artificial intelligence (AI) provides a new way to solve these troubles in auditory and speech rehabilitation for the hearing-impaired population. This paper review the technological evolution of AI in this field

from traditional signal processing and machine learning to deep learning

large models

and clinical translation. Introduce the core technical architecture

including front-end perception

mid-level processing and back-end application. Now

AI has made significant progress in speech enhancement

outcome prediction

multimodal fusion and personalized rehabilitation plan generation. But

There are still difficulties remain

such as data scarcity and heterogeneity

insufficient model generalization capability

lack clinical interpretability and barriers to translation. Future works should focus on constructing large-scale multimodal databases

better out-of-distribution generalization of models and strengthen the integration of AI tools into clinical practice to make personalized and intelligent in auditory and speech rehabilitation for the hearing-impaired population.

关键词

Keywords

references

World Health Organization . World Report on Hearing [R ] . Geneva : WHO , 2023 .

王段霞 , 梁巍 , 卢晓月 , 等 . 我国听觉口语法发展及听觉口语师队伍建设现状 [J ] . 中国听力语言康复科学杂志 , 2026 , 24 ( 2 ): 215 - 218 .

陈仁吉 . 我国言语障碍康复治疗发展历程与现状 [J ] . 中国听力语言康复科学杂志 , 2025 , 23 ( 4 ): 348 - 351 .

Borjigi A , Kokkinakis K , Bharadwaj HM , et al . Deep learning restores speech intelligibility in multi-talker interference for cochlear implant users [J ] . Sci Rep , 2024 , 14 : 13241 .

Demirtaş YM . Prediction of Auditory Performance in Cochlear Implants Using Machine Learning Methods: A Systematic Review [J ] . Audiology Research , 2025 , 15 ( 3 ): 56 - 56 .

Shew MA , Pavelchek C , Michelson A , et al . Machine Learning Feasibility in Cochlear Implant Speech Perception Outcomes-Moving Beyond Single Biomarkers for Cochlear Implant Performance Prediction [J ] . Ear Hear , 2025 , 46 ( 5 ): 1266 - 1281 .

Zaineldin H , GameL SA , Talaat FM , et al . Silent no more: A comprehensive review of artificial intelligence, deep learning, and machine learning in facilitating deaf and mute communication [J ] . Artif Intell Rev , 2024 , 57 ( 7 ): 188 - 188 .

lachguer N , Azizi O , EL Mamoune S . AI-VoiceTherapy: An Automated Platform for Voice Rehabilitation Using Artificial Intelligence [J ] . Int J Comput Eng Data Sci , 2025 , 92 ( 55 ): 463 - 463 .

Mo JT , Chong DS , Sun C , et al . Machine-Learning Predictions of Cochlear Implant Functional Outcomes: A Systematic Review [J ] . Ear Hear , 2025 , 46 ( 4 ): 952 - 962 .

Nossier SA , Wall J , Moniri M , et al . An Experimental Analysis of Deep Learning Architectures for Supervised Speech Enhancement [J ] . Electronics , 2021 , 10 ( 1 ): 17 - 17 .

Pandey A , Wang D . On Cross-Corpus Generalization of Deep Learning Based Speech Enhancement [J ] . IEEE/ACM Trans Audio Speech Lang Process , 2020 , 28 : 2489 - 2499 .

Mawalim CO , Okada S , Unoki M . Are Recent Deep Learning-Based Speech Enhancement Methods Ready to Confront Real-World Noisy Environments [C ] . Proceedings of Interspeech 2024 . 2024 .

Behera A , Easow RA , Parvathala V , et al . Test-Time Training for Speech Enhancement [C ] . Proceedings of Interspeech 2025 . 2025 .

Zhang H , Wang Y , Liu J , et al . HI-TransPA: Hearing Impairments Translation Personal Assistant [C ] . 2025 IEEE International Conference on Multimedia & Expo (ICME) , 2025 . 1 - 6 .

Rudroff T . Artificial Intelligence in Audiology Neuroprosthetics: A Bidirectional Approach for Speech and Hearing Impairments [J ] . Brain Sci , 2025 , 15 ( 4 ): 449 - 449 .

Frosolini A , Franz L , Caragli V , et al . Artificial Intelligence in Audiology: A Scoping Review of Current Applications and Future Directions [J ] . Sensors , 2024 , 24 ( 22 ): 7126 .

Deka C , Shrivastava A , Abraham AK , et al . AI-based automated speech therapy tools for persons with speech sound disorder: a systematic literature review [J ] . Speech Lang Hear , 2025 , 28 ( 1 ): 2359274 .

Monaghan JJM , Goehring T , Yang X , et al . Auditory-inspired machine learning techniques can improve speech intelligibility and quality for hearing-impaired listeners [C ] . 2022 International Conference on Acoustics, Speech, and Signal Processing (ICASSP) , 2022 . 1 - 5 .

Whitmal N , Rutledge J , Cohen J . Denoising speech signals for digital hearing aids: A wavelet based approach [J ] . J Signal Process Syst , 2019 , 91 ( 4 ): 443 - 452 .

Stipancic KL , Yunusova Y , Berry JD , et al . Minimally detectable change and minimal clinically important difference of a decline in sentence intelligibility and speaking rate for individuals with amyotrophic lateral sclerosis [J ] . J Speech Lang Hear Res , 2018 , 61 ( 11 ): 2757 - 2771 .

Kouhsai SM . Fundamental research in electrical engineering [C ] . 2019 International Conference on Electrical Engineering (ICEE) . Springer , 2019 . 1 - 5 .

Guo A , Kamar E , Vaughan JW , et al . Toward fairness in AI for people with disabilities: A research roadmap [C ] . Proceedings of the ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) , 2020 , 1 - 1 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

成人听障口语者病理性腔调研究：现状审视、范式转换与未来进路

迈向精准化与普惠化：人工智能赋能孤独症儿童康复教育的发展图景

人工智能赋能孤独症谱系障碍儿童能力评价：核心问题与实践框架

心理资本在听障儿童父母感知脆弱与主观幸福感间的中介效应分析

阶梯式会话训练策略在小组教学中提升语言障碍儿童会话能力的行动研究