Search research articles

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 Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

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

FBG-Based Multi-Parameter Sensor for Harsh Transformer Conditions: Decoupling Packaging for Simultaneous Temperature, Pressure, and Moisture Measurement.

Sensors (Basel, Switzerland)·2026

Same author

Intravenous immunoglobulin frequency in multifocal motor neuropathy: a retrospective study of nerve conduction outcomes.

BMC neurology·2026

Same author

Preoperative health status assessed with different scales and postoperative cardiac and cerebrovascular complications in older patients: A retrospective study of a large multicentre cohort.

European journal of anaesthesiology·2026

Same author

Entropy-Driven Conformational Disorder Enables Outstanding High-Temperature Energy Storage in Dielectric Polymers.

Advanced materials (Deerfield Beach, Fla.)·2026

Same author

Ketamine alters the aperiodic EEG exponent in major depression: implications for cortical E/I balance and treatment prediction.

Therapeutic advances in psychopharmacology·2026

Same author

Mutant superoxide dismutase 1-catalyzed hydrogen therapy for amyotrophic lateral sclerosis achieved by intercepting oxidative stress-neuroinflammation crosstalk.

Acta biomaterialia·2026

Search research articles

相关实验视频

Updated: Sep 12, 2025

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

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

Published on: September 27, 2024

Praditor:基于DBSCAN的自动化,用于发言发作检测.

Zhengyuan Liu¹, Xinqi Yu^2,3, Wing Chung Hu⁴

¹Centre for Cognitive and Brain Sciences, University of Macau, Taipa, Macau SAR, China.

Behavior research methods

|August 4, 2025

概括

一个新的工具Praditor使用自动化算法准确检测语音发言时间 (SOT),从而减少了手动注释的费用. 这种半自动方法有助于跨语言的语音制作研究.

关键词:

自动检测自动检测自动检测在DBSCAN中,可以使用DBSCAN.第一个衍生品持有值.语言生产语言生产.发言的开始时间

更多相关视频

Combined Invasive Subcortical and Non-invasive Surface Neurophysiological Recordings for the Assessment of Cognitive and Emotional Functions in Humans

Combined Invasive Subcortical and Non-invasive Surface Neurophysiological Recordings for the Assessment of Cognitive and Emotional Functions in Humans

Published on: May 19, 2016

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Published on: July 22, 2025

相关实验视频

Last Updated: Sep 12, 2025

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

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

Published on: September 27, 2024

Combined Invasive Subcortical and Non-invasive Surface Neurophysiological Recordings for the Assessment of Cognitive and Emotional Functions in Humans

Combined Invasive Subcortical and Non-invasive Surface Neurophysiological Recordings for the Assessment of Cognitive and Emotional Functions in Humans

Published on: May 19, 2016

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Published on: July 22, 2025

科学领域:

语言学的语言学.
语音科学语言科学
计算语言学计算语言学

背景情况:

语音发声时间 (SOT) 对于语音制作研究至关重要.
手动的SOT注释是准确的,但耗时和累人的.
现有的方法可能缺乏用户友好性或语言独立性.

研究的目的:

介绍Praditor,这是一个半自动工具用于语音发声检测.
为SOT注释提供一个用户友好和高效的解决方案.
促进语言独立的语音分析.

主要方法:

使用DBSCAN和第一衍生值算法开发了Praditor.
实现了一个图形用户界面 (GUI) 便于参数调整.
在普通话和英语数据集上进行测试,以评估准确性.

主要成果:

普拉迪托表现出高准确度,约90%的注释在手册注释的±20毫秒内.
文件级和集体级的调整都显示了可接受的准确性.
该工具有效地处理单启动和多启动的音频文件.

结论:

Praditor提供了一个可靠和高效的半自动解决方案,用于语音发作注释.
该工具与语言无关,可供具有不同技术专业知识的用户使用.
Praditor是公开可用的,促进了在语音研究中的更广泛使用.