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

Spontaneous uterine rupture during pregnancy after radiofrequency ablation for adenomyosis: A case report and literature review.

Taiwanese journal of obstetrics & gynecology·2026
Same author

Corrigendum to "The effect of gestational diabetes on maternal and neonatal outcomes" [Taiwan J Obstet Gynecol 65 (2026) 256-264].

Taiwanese journal of obstetrics & gynecology·2026
Same author

Influence of the dose and duration of intrapartum antibiotic prophylaxis on umbilical cord blood ampicillin levels.

Journal of perinatology : official journal of the California Perinatal Association·2026
Same author

The effects of core stabilizing exercise in postpartum women with lumbopelvic pain: A systematic review with meta-analysis.

Brazilian journal of physical therapy·2026
Same author

Speaker-dependent laser Doppler vibrometer-based voice conversion for dysarthric speech under noisy conditions.

JASA express letters·2026
Same author

The effect of gestational diabetes on maternal and neonatal outcomes.

Taiwanese journal of obstetrics & gynecology·2026

相关实验视频

Updated: Jul 11, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

596

改进基于数据增强的失联症语音转换系统的效率.

Wei-Zhong Zheng, Ji-Yan Han, Chen-Yu Chen

    IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society
    |November 8, 2023
    PubMed
    概括

    这项研究介绍了Dysarthria Voice Conversion 3.1 (DVC 3.1),这是一个数据增强系统,可以改善失声症患者的语音可理解性. DVC 3.1 通过减少记录负担和提高清晰度,显著增强了通信.

    科学领域:

    • 语音和听力科学 语言和听力科学
    • 生物医学工程 生物医学工程
    • 人工智能的人工智能

    背景情况:

    • 失声症是一种神经语音障碍,损害了声音肌肉的控制,导致不清晰的语音和沟通困难.
    • 现有的语音转换 (VC) 方法治疗脱节性关节炎往往需要来自患者和目标发言人的大量语音数据,这造成了显著的录音负担.
    • 需要高效的VC系统,尽量减少数据需求,同时有效地提高语音可理解性.

    研究的目的:

    • 提出一种基于数据增强的新型语音转换 (VC) 系统,称为失联症语音转换3.1 (DVC 3.1),以减轻失联症患者的录音负担.
    • 通过合成的语音数据,增强患有脱节症的个体的语音可理解性.
    • 为了评估DVC 3.1与基线系统 (DVC 3.0) 和未经处理的发言障碍症相比,DVC 3.1的有效性.

    主要方法:

    • 开发了DVC 3.1,使用数据增强方法,结合了文本到语音 (TTS) 合成和StarGAN-VC架构.
    • 综合了目标类和患者类语音数据的综合体,以减少对广泛录音的需求.
    • 使用谷歌自动语音识别 (Google ASR) 进行客观评估,并进行听力测试以主观评估语音可理解性.

    主要成果:

    • DVC 3.1 显著改善了 Google ASR 两名脱节动脉障碍患者的表现,相对于未处理的语音和 DVC 3.0,分别显示了大约 [62.4%,43.3%] 和 [55.9%,57.3%] 的增强.

    更多相关视频

    Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception
    05:48

    Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

    Published on: August 9, 2024

    1.5K
    Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody
    09:09

    Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody

    Published on: September 27, 2024

    464

    相关实验视频

    Last Updated: Jul 11, 2025

    Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
    03:14

    Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

    Published on: December 6, 2024

    596
    Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception
    05:48

    Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

    Published on: August 9, 2024

    1.5K
    Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody
    09:09

    Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody

    Published on: September 27, 2024

    464
  • 主观评估表明,与未处理的语音和DVC 3.0.1相比,DVC 3.1的语音可理解性大幅增加,约为 [54.2%,22.3%] 和 [63.4%,70.1%].
  • 在DVC 3.1中的数据增强策略有效地合成了必要的语音数据,减少了录制需求.

    • 结论:

    • 拟议的DVC 3.1系统显示了在失联症患者中提高语音可理解性的巨大潜力.
    • DVC 3.1 通过克服需要大量数据集的传统 VC 方法的局限性,提高了口头沟通的质量.
    • 这种以数据增强为驱动的方法为失联症语音康复提供了实用和有效的解决方案.