Intelligibility of Different Synthesized Mandarin Speech by Cochlear Implant Listeners

SHI Ying; CHEN Jing-yuan; CHEN Biao; ZOU Xin-yue; LI Yong-xin

doi:10.3969/j.issn.1672-4933.2025.06.017

您当前的位置：

首页 >

文章列表页 >

Intelligibility of Different Synthesized Mandarin Speech by Cochlear Implant Listeners

Rehabilitation Education | 更新时间：2026-07-30

- Intelligibility of Different Synthesized Mandarin Speech by Cochlear Implant Listeners
- Chinese Scientific Journal of Hearing and Speech Rehabilitation Vol. 23, Issue 6, Pages: 631-636(2025)
- 作者机构：
  
  首都医科大学附属北京同仁医院耳鼻咽喉头颈外科北京 100730
- 作者简介：
- 基金信息：
- DOI：10.3969/j.issn.1672-4933.2025.06.017
  CLC： G762
- Received：14 December 2023，
  
  Online First：17 November 2025，
  
  Published：15 November 2025
- 稿件说明：
移动端阅览
石颖,陈婧媛,陈彪等.普通话人工耳蜗植入者对不同模式合成语音短句材料的识别分析[J].中国听力语言康复科学杂志,2025,23(06):631-636.

SHI Ying,CHEN Jing-yuan,CHEN Biao,et al.Intelligibility of Different Synthesized Mandarin Speech by Cochlear Implant Listeners[J].Chinese Scientific Journal of Hearing and Speech Rehabilitation,2025,23(06):631-636.
石颖,陈婧媛,陈彪等.普通话人工耳蜗植入者对不同模式合成语音短句材料的识别分析[J].中国听力语言康复科学杂志,2025,23(06):631-636. DOI： 10.3969/j.issn.1672-4933.2025.06.017.

SHI Ying,CHEN Jing-yuan,CHEN Biao,et al.Intelligibility of Different Synthesized Mandarin Speech by Cochlear Implant Listeners[J].Chinese Scientific Journal of Hearing and Speech Rehabilitation,2025,23(06):631-636. DOI： 10.3969/j.issn.1672-4933.2025.06.017.

摘要

目的

评估汉语普通话人工耳蜗植入（CI）者对不同模式合成语音短句的识别能力。

方法

选取母语为汉语普通话的CI者17人，测试其安静环境中对自然语音与5种不同模式合成语音短句材料的言语识别率，包括不同讲话者性别、语速和讲话方式，分别记录被试的言语识别率后进行对比分析。

结果

被试对自然语音识别率最高，对合成语音的B-Accent模式最差，短句的言语模式对言语识别率有显著影响［F（5，80）=53.8，

0.001］。多重比较分析发现，被试对自然语音的识别能力与其他所有合成语音的识别均有显著差异（

0.001），F-Slow与F-Normal模式的识别率无显著差异，F-Normal与M-Normal模式识别率无显著差异，F-Normal模式的识别率显著高于F-Emotion和B-Accent模式，M-Normal模式的识别率显著高于F-Emotion和B-Accent模式；对F-Emotion模式的识别率显著高于B-Accent模式（

0.05）。受试者人口学变量均与其对合成语音短句的识别率无相关性（

0.05）。

结论

CI者对合成语音短句的识别能力易受合成语音的韵律信息影响，其变化越复杂，识别难度越大。

Abstract

Objective

To investigate the intelligibility of synthesized Mandarin speech by cochlear implant patients and analyze the influencing factors.

Methods

17 Mandarin-speaking cochlear implant users participated in the test. All the sentences were naturally produced by a single female talker in slow clear speaking style (F-Nat) or were synthesized using the iFlyTek TTS engine.Five synthesized voices (F-Slow

F-Normal

M-Normal

F-Emotion and B-Accent)were selected to represent different talker genders

speaking rates

and speaking styles

speech recognition scores were analyzed.

Results

For CI users

the worst speech recognition scores were with the B-accent sentence.There was a significant effect of speech type [F(5

80)=53.8

0.001

]

. Post-hoc Bonferroni pair-wise comparisons showed that performance was significantly better with F-Nat than with any of the synthesized voices

significantly better with F-Norm than with F-Emot

or B-Acc

significantly better with F-Norm than with F-Emot or B-Acc

significantly better with M-Norm than with B-Acc or F-Emot

and significantly better with F-Emot than with B-Acc (

0.05). There was no significant difference between F-Slow and F-Normal(

=0.97)

so was F-Normal and M-Normal. There were no significant correlations among any of the demographic variables and speech types (

0.05).

Conclusions

CI users were susceptible to dynamic changes in speech

the more complex the variation is

the more difficult it is to identify.

关键词

Keywords

references

王永鑫 , 蔡莲红 . 语法信息与韵律结构的分析与预测 [J ] . 中文信息学报 , 2010 , 24 ( 1 ): 65 - 70 .

陶建华 , 蔡莲红 , 赵晟 . 汉语语音合成中的文本分析和韵律处理 [C ] . 辉煌二十年——中国中文信息学会二十周年学术会议论文集 . 2001 . 279 - 286 .

冯哲 , 孙吉贵 , 张长胜 , 等 . 汉语语音合成的研究进展 [J ] . 吉林大学学报(信息科学版) , 2007 , 25 ( 2 ): 198 - 206 .

Paris CR , Thomas MH , Gilson RD , et al . Linguistic Cues and Memory for Synthetic and Natural Speech [J ] . Human Factors: The Journal of the Human Factors and Ergonomics Society , 2000 , 42 ( 3 ): 421 - 431 .

Ji C , Galvin JJ , Xu A , et al . Effect of Speaking Rate on Recognition of Synthetic and Natural Speech by Normal-Hearing and Cochlear Implant Listeners [J ] . Ear and hearing , 2012 , 34 ( 3 ): 313 - 323 .

Shi Y , Peng KA , Chen B , et al . Interaction between Speech Variations and Background Noise on Speech Intelligibility by Mandarin-Speaking Cochlear Implant Patients [J ] . Speech Communication , 2018 , 104 ( 11 ): 89 - 94 .

Fu QJ , Zhu M , Wang X . Development and validation of the Mandarin speech perception test [J ] . J Acoust Soc Am , 2011 , 129 ( 6 ): L267 - L273 .

王顺成 , 石颖 , 李永新 , 等 . 开放式言语评估系统短句材料在人工耳蜗植入者中等价性的初步分析 [J ] . 听力学及言语疾病杂志 , 2013 , 21 ( 3 ): 74 - 77 .

Li Y , Zhang G . Effects of speaking style on speech intelligibility for Mandarin-speaking cochlear implant users [J ] . Journal of the Acoustical Society of America , 2011 , 129 ( 6 ): EL242 .

Su Q , Galvin JJ , Zhang G , et al . Effects of Within-Talker Variability on Speech Intelligibility in Mandarin-Speaking Adult and Pediatric Cochlear Implant Patients [J ] . Trends Hear , 2016 , 20 : 2331216516654022 .

Liu C , Galvin J , Fu QJ , et al . Effect of spectral normalization on different talker speech recognition by cochlear implant users [J ] . The Journal of the Acoustical Society of America , 2008 , 123 ( 5 ): 2836 .

Borrie S , McAuliffe M , Liss J , et al . The role of linguistic and indexical information in improved recognition of dysarthric speech [J ] . j acoust soc am , 2011 , 130 ( 4 ): 2447 - 2447 .

Fu QJ , Chinchilla S , Galvin JJ . The role of spectral and temporal cues in voice gender discrimination by normal-hearing listeners and cochlear implant users [J ] . J Assoc Res Otolaryngol , 2004 , 5 ( 3 ): 253 - 260 .

Fu QJ , Chinchilla S , Nogaki G , et al . Voice gender identification by cochlear implant users: the role of spectral and temporal resolution [J ] . j acoust soc am , 2005 , 118 ( 3 Pt 1 ): 1711 - 1718 .

Vongphoe M , Zeng FG . Speaker recognition with temporal cues in acoustic and electric hearing [J ] . J Acoust Soc Am , 2005 , 118 ( 2 ): 1055 - 1061 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A Preliminary Study to Investigate the Correlation Between Position-Specific Effect of Interphase Gap and Competing Acoustic Environments Speech Recognition in Cochlear Implant Receivers

Evaluation of Rehabilitation Outcomes after Cochlear Implantation in Later-Implanted Patients with Prelingual Deafness

Quality of Life Assessment of Children with Cochlear Implants in Shanghai: A Retrospective Analysis Based on the Nijmegen Scale

Preoperative Multidisciplinary Assessment for Cochlear Implantation

Preliminary Observation of Electrically Evoked Cortical Auditory Potential P1-N1 in Patients with No Residual Hearing

Related Author

GONG Meng-fang

HE Qian

ZHU Xiao-ting

SHENG Xiao-liang

KANG Shi-yu

LIU Ji-sheng

TAO Duo-duo

WEN Sen-lin

Related Institution

苏州大学苏州医学院

苏州大学附属第一医院耳鼻咽喉科

解放军第九八〇医院耳鼻咽喉头颈外科

上海市特殊儿童康复中心

诺尔康听觉言语医学研究院/浙江省智能康复与神经电子转化重点实验室/杭州余杭启航公益服务中心

⁰