A Preliminary Study on the Construction of a Speech Corpus and Voice Information Database for Hearing-Impaired Speakers

LI Yao; XUE Jing; ZHAO Qian; JIANG Chun; ZHANG Yan-ling; SUN Jing; YU Li-mei; XING Ya-jing

doi:10.3969/j.issn.1672-4933.2026.03.004

您当前的位置：

首页 >

文章列表页 >

A Preliminary Study on the Construction of a Speech Corpus and Voice Information Database for Hearing-Impaired Speakers

Research on Speech Restoration for Hearing Impaired Speakers | 更新时间：2026-07-30

- A Preliminary Study on the Construction of a Speech Corpus and Voice Information Database for Hearing-Impaired Speakers
- Chinese Scientific Journal of Hearing and Speech Rehabilitation Vol. 24, Issue 3, Pages: 236-240(2026)
- 作者机构：
  
  中国听力语言康复科学杂志社北京 100029
- 作者简介：
- 基金信息：
- DOI：10.3969/j.issn.1672-4933.2026.03.004
  CLC： R494
- Received：21 March 2026，
  
  Online First：11 May 2026，
  
  Published：15 May 2026
- 稿件说明：
移动端阅览
李瑶,薛静,赵倩等.听障口语者语料库、语音信息库建设初探[J].中国听力语言康复科学杂志,2026,24(03):236-240.

LI Yao,XUE Jing,ZHAO Qian,et al.A Preliminary Study on the Construction of a Speech Corpus and Voice Information Database for Hearing-Impaired Speakers[J].Chinese Scientific Journal of Hearing and Speech Rehabilitation,2026,24(03):236-240.
李瑶,薛静,赵倩等.听障口语者语料库、语音信息库建设初探[J].中国听力语言康复科学杂志,2026,24(03):236-240. DOI： 10.3969/j.issn.1672-4933.2026.03.004.

LI Yao,XUE Jing,ZHAO Qian,et al.A Preliminary Study on the Construction of a Speech Corpus and Voice Information Database for Hearing-Impaired Speakers[J].Chinese Scientific Journal of Hearing and Speech Rehabilitation,2026,24(03):236-240. DOI： 10.3969/j.issn.1672-4933.2026.03.004.

摘要

听障口语者的语音数据是开展听障语音特征分析与人工智能（artificial intellipence， AI）声音修复技术研究的基础资源。我国听力残疾人口基数大，口语使用者众多，但面向汉语听障人群的专用语音数据长期匮乏、标准缺失、共享不足，成为AI康复技术落地的核心瓶颈。本文针对当前听障语音数据建设缺乏系统规范的现状，梳理了国内外相关理论与实践，分析了我国面临的本土化困境。在此基础上，提出借助人工智能技术，通过确立行业标准、构建人机协同工作流、构建分级开放的数据共享机制、加速跨学科人才培养等路径，推动听障语音数据库的系统化、标准化与智能化建设，旨在为我国听障语音数据资源的系统化建设提供参考。

Abstract

Speech data from hearing-impaired speakers constitute a fundamental resource for research on hearing-impaired speech feature analysis and AI-driven voice restoration technologies. China has a large population of hearing-impaired individuals

among whom many use spoken language as their primary means of communication. However

dedicated speech data for Mandarin-speaking hearing-impaired individuals have long been lacking in quantity

standardized norms

and sharing mechanisms

which has become a critical bottleneck hindering the deployment of AI-based rehabilitation technologies. In response to the current lack of systematic standards for hearing-impaired speech data construction

this paper reviews relevant theories and practices from both domestic and international sources

and analyzes the localization challenges faced in China. On this basis

this paper proposes leveraging artificial intelligence technologies to promote the systematic

standardized

and intelligent construction of hearing-impaired speech databases through the establishment of industry standards

the development of human-AI collaborative workflows

the creation of tiered open data sharing mechanisms

and the acceleration of interdisciplinary talent cultivation. This study aims to provide methodological references for the systematic construction of speech data resources for hearing-impaired individuals in China.

关键词

Keywords

references

李兴腾 , 冯锋 , 黄鹂强 . 突破人工智能大模型的"数据瓶颈"——构建国家级语料库运营平台的思考 [J ] . 中国科学院院刊 , 2025 , 40 ( 3 ): 522 - 529 .

孙奇茹 . AI声带、视障导航科技点亮残障人士"无碍"生活 [EB/OL ] . 北京日报 . 2024-12-03 .

MacWhinney B . Understanding spoken language through TalkBank [J ] . Behavior Research Methods , 2019 , 51 ( 4 ): 1919 - 1927 .

MacWhinney B , Roberts JA , Sloane M , et al . Fluency Bank: A new resource for fluency research and practice [J ] . Journal of Fluency Disorders , 2018 , 56 : 69 - 80 .

Beckman ME , Plummer AR , Munson B , et al . Methods for eliciting, annotating, and analyzing databases for child speech development [J ] . Computer Speech & Language , 2017 , 45 : 278 - 299 .

Ghio A , Pouchoulin G , Teston B , et al . How to manage sound, physiological and clinical data of 2500 dysphonic and dysarthric speakers? [J ] . Speech Communication , 2012 , 54 ( 5 ): 664 - 679 .

Jiang PP , Tobin J , Tomanek K , et al . Learnings from curating a trustworthy, well-annotated, and useful dataset of disordered English speech [C ] . Proceedings of Interspeech 2024. ISCA , 2024 . 2490 - 2493 .

Sanguedolce G , Price CJ , Brook S , et al . SONIVA: Speech recOgNItion Validation in Aphasia [J ] . medRxiv , 2025 . 2025. 06 . 03 : 25328889 .

王仁华 , 夏德瑜 , 倪晋富 . 汉语语音识别数据库研制 [J ] . 自动化学报 , 1992 , 18 ( 3 ): 376 - 378 .

徐彦君 , 杜利民 , 李国强 , 等 . 汉语听觉视觉双模态数据库CAVSR1.0 [J ] . 声学学报 , 2000 , 25 ( 1 ): 42 - 49 .

赵剑 , 王丽荣 . 基于三维可视语音库的发音康复方法 [J ] . 长春大学学报 , 2010 , 20 ( 2 ): 75 - 77 .

薛静 , 刘爱姝 , 王丽燕 , 等 . 中国听力语言康复科学杂志文献库建设初探 [J ] . 中国听力语言康复科学杂志 , 2014 , 11 ( 5 ): 381 - 383 .

梁巍 . 语料库语言学 [J ] . 中国听力语言康复科学杂志 , 2010 , 8 ( 5 ): 57 - 60 .

张帆 . 浙江中高职聋生汉字偏误语料库的建设 [J ] . 教育评论 , 2013 ( 3 ): 120 - 122 .

任媛媛 , 赵晓驰 . 手语语料数据的类型及其采集方法综述 [J ] . 现代特殊教育 , 2023 ,( 14 ): 70 - 77 .

吕会华 , 吴铃 , 张会文 . 聋人汉语书面语语料库建设研究 [J ] . 中国特殊教育 , 2010 ,( 3 ): 31 - 33 .

陈凌云 , 卢雪飞 , 王玉玲 , 等 . 基于语料库的聋生汉语"是"字句偏误分析 [J ] . 中国听力语言康复科学杂志 , 2024 , 22 ( 4 ): 388 - 392 .

Yu J , Sun H , Tian XY , et al . How much does syntactic complexity contribute to the oral narrative performance of prelingually deaf Mandarin-speaking children with cochlear implants? [J ] . Journal of Speech, Language, and Hearing Research , 2025 , 68 ( 1 ): 217 - 237 .

Wan Y , Sun MY , Kang XC , et al . CDSD: Chinese dysarthria speech database [C ] . Proceedings of Interspeech 2024. ISCA , 2024 . 4109 - 4113 .

朱云 , 韩鹏 , 张少强 , 等 . 基于构音训练的语言康复训练对听障儿童听觉言语能力及智力发育的影响 [J ] . 中国听力语言康复科学杂志 , 2024 , 22 ( 1 ): 87 - 90 .

Yue ZJ , Barberis M , Patel T , et al . Challenges and practical guidelines for atypical speech data collection, annotation, usage and sharing: A multi-project perspective [C ] . Proceedings of Interspeech 2025. ISCA , 2025 . 3943 - 3947 .

Brundage SB , Bernstein Ratner N , Boyle MP , et al . Consensus guidelines for the assessment of individuals who stutter across the lifespan [J ] . American Journal of Speech-Language Pathology , 2021 , 30 ( 6 ): 2379 - 2393 .

Ullah R , Zhang S , Asif M , et al . Multimodal learning-based speech enhancement and separation: recent innovations, new horizons, challenges and real-world applications [J ] . Computers in Biology and Medicine , 2025 , 190 : 110082 .

Poorjam AH , Little MA , Jensen JR , et al . Quality control in remote speech data collection [J ] . IEEE Journal of Selected Topics in Signal Processing , 2019 , 13 ( 2 ): 236 - 243 .

Cheng L , Han J , Nasirov J . Ethical considerations related to personal data collection and reuse: trust and transparency in language and speech technologies [J ] . International Journal of Legal Discourse , 2024 , 9 ( 2 ): 217 - 235 .

Hasegawa-Johnson M , Zheng X , Kim H , et al . Community-Supported Shared Infrastructure in Support of Speech Accessibility [J ] . Journal of Speech, Language, and Hearing Research , 2024 , 67 ( 11 ): 4162 - 4175 .

Paullada A , Raji ID , Bender EM , et al . Data and its (dis)contents: A survey of dataset development and use in machine learning research [J ] . Patterns , 2021 , 2 ( 11 ): 100336 .

Gao YM , Feng XL , Li BX , et al . Advancing speech data collection and annotation: General methods, practical experience, and future perspectives [J ] . Journal of Shanghai Jiaotong University (Science) , 2026 , 1 - 8 .

王颇 , 白静 , 薛珮芸 . 融合发音动作特征和声学特征的病理语音检测 [J ] . 计算机工程与设计 , 2021 , 42 ( 3 ): 776 - 781 .

Hidaka S , Lee Y , Nakanishi M , et al . Automatic GRBAS Scoring of Pathological Voices using Deep Learning and a Small Set of Labeled Voice Data [J ] . Journal of Voice , 2025 , 39 ( 3 ): 846.e1 - 846.e23 .

Triantafyllopoulos A , Schuller BW . Hearing aids in the era of foundation models [J ] . GMS Zeitschrift für Audiologie , 2024 , 6 : 28 - 28 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Analysis of Speech Clarity Characteristics and Needs in Hearing-Impaired Oral Speakers

Clinical Issues in Cochlear Implantation for Elderly Patients With Hearing Loss (Part I): Preoperative Decision-Making and Key Perioperative Considerations

Analysis of Hearing Aid Effectiveness in Patients with Age-related Hearing Loss

Research Progress on Audiovisual Emotion Integration in Preschool Children with Hearing Impairment

The Effects of the PEERS Program on Social Skills of Preschool Children with Autism Spectrum Disorder and Caregiver Parenting Stress

Related Author

XUE Jing

WANG Zi-yao

ZHAO Qian

JIANG Chun

LI Yao

ZHANG Yan-ling

SUN Jing

YU Li-mei

Related Institution

中国听力语言康复研究中心

北京第二外国语学院

⁰