Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Incorporating softmax in psychophysical detection models for normal and electric hearing.

MethodsX·2026
Same author

The current status and future of using computational models to individually optimise cochlear implant stimulation.

Expert review of medical devices·2026
Same author

Leveraging spatial cues from cochlear implant microphones to efficiently enhance speech separation in naturalistic listening scenes.

Scientific reports·2025
Same author

The Influence of Speech Material, Intelligibility, and Masker Type on the Pupil Dilation Response in Cochlear Implant Users.

Ear and hearing·2025
Same author

From spikes to speech: NeuroVoc - A biologically plausible vocoder framework for auditory perception and cochlear implant simulation.

Hearing research·2025
Same author

AI-driven neural implants for vision and hearing: a qualitative study of user perspectives.

Disability and rehabilitation. Assistive technology·2025

相关实验视频

Updated: Jan 12, 2026

Systematic Hearing Performance Evaluation Process for Adolescents with Cochlear Implantation at Early Ages
06:04

Systematic Hearing Performance Evaluation Process for Adolescents with Cochlear Implantation at Early Ages

Published on: March 24, 2023

741

对于耳植入物,一种基于人工智能的新反响减小算法提高了语音可理解性和用户体验.

Nienke C Langerak1, H Christiaan Stronks1,2, Esther F van Marrewijk1

  • 1Department of Otorhinolaryngology and Head & Neck Surgery, Leiden University Medical Center, Leiden, the Netherlands.

Ear and hearing
|November 3, 2025
PubMed
概括

新的人工智能算法显著改善了耳植入物 (CI) 用户在反响环境中的语音理解. 这些人工智能驱动的脱声工具提高了清晰度和听力舒适度,而不会影响安静环境中的言语.

关键词:
人工智能的人工智能是人工智能.耳植入器是一种耳植入器.预处理 预处理声 反响 声 声感官神经神经听力损失是什么

更多相关视频

Electrically Evoked Stapedius Reflex Measurements in Cochlear Implantation and Its Application in the Postoperative Fitting Process
07:00

Electrically Evoked Stapedius Reflex Measurements in Cochlear Implantation and Its Application in the Postoperative Fitting Process

Published on: June 21, 2024

1.4K
Robotic Cochlear Implantation for Direct Cochlear Access
08:06

Robotic Cochlear Implantation for Direct Cochlear Access

Published on: June 16, 2022

3.9K

相关实验视频

Last Updated: Jan 12, 2026

Systematic Hearing Performance Evaluation Process for Adolescents with Cochlear Implantation at Early Ages
06:04

Systematic Hearing Performance Evaluation Process for Adolescents with Cochlear Implantation at Early Ages

Published on: March 24, 2023

741
Electrically Evoked Stapedius Reflex Measurements in Cochlear Implantation and Its Application in the Postoperative Fitting Process
07:00

Electrically Evoked Stapedius Reflex Measurements in Cochlear Implantation and Its Application in the Postoperative Fitting Process

Published on: June 21, 2024

1.4K
Robotic Cochlear Implantation for Direct Cochlear Access
08:06

Robotic Cochlear Implantation for Direct Cochlear Access

Published on: June 16, 2022

3.9K

科学领域:

  • 听力学 听力学是指听力学.
  • 人工智能的人工智能
  • 信号处理 信号处理

背景情况:

  • 耳植入物 (CIs) 是严重到严重的听力损失的标准.
  • 对于CI用户来说,在反响环境中的语音理解仍然是一个挑战.
  • 当前的CI技术与背景噪音和回声作斗争.

研究的目的:

  • 评估基于人工智能的新型算法,用于降低CI用户语音信号中的反响.
  • 评估这些算法对语音可理解性和主观听力体验的影响.
  • 为了确定AI脱声是否可以在具有挑战性的声学条件下改善CI性能.

主要方法:

  • 一项涉及15名IC使用者的前性交叉研究.
  • 测试了两个AI算法:DNN-WPE (迟反响) 和DNN-WPEPF (早期和迟反响).
  • 使用佛兰德/荷兰矩阵测试测量语音可理解性;主观评分评估听力,自然性和可理解性.

主要成果:

  • DNN-WPE提高了11%的语音可理解性 (p < 0.001);DNN-WPEPF提高了17%的语音可理解性 (p < 0.001).
  • 与DNN-WPE相比,DNN-WPEPF的益处显著超过了DNN-WPE (p = 0.018).
  • 这两种算法都是倾听力,自然性和在反响条件下可理解性的优势,并且不会降低清洁言语.

结论:

  • 人工智能驱动的退声算法 (DNN-WPE,DNN-WPEPF) 在反响环境中显著有利于CI用户.
  • 这些算法增强了语音可理解性和主观感知,而不会影响静音中的性能.
  • 为了广泛的临床使用,需要进一步的研究和实时实施.