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

Improving Translational Accuracy02:07

Improving Translational Accuracy

2.6K
2.6K
Types Of Transformers01:16

Types Of Transformers

987
Transformers can provide desired voltages to a circuit by modifying the number of turns in the secondary windings.
If the ratio of the number of turns in the secondary winding to that of the primary winding is greater than one, then the transformer is said to be a step-up transformer. In a step-up transformer, the voltage at the secondary winding is greater than the voltage applied at the primary winding.
However, if this ratio is less than one, the transformer is said to be a step-down...
987

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

Adaptive regularized spectral reduction for stabilizing ill-conditioned bone-conducted speech signals.

PeerJ. Computer science·2025
Same author

Real-time multilingual speech recognition and speaker diarization system based on Whisper segmentation.

PeerJ. Computer science·2024
Same author

Recurrent Neural Model to Analyze the Effect of Physical Training and Treatment in Relation to Sports Injuries.

Computational intelligence and neuroscience·2022
Same author

Data augmentation and deep neural networks for the classification of Pakistani racial speakers recognition.

PeerJ. Computer science·2022
Same author

Lightweight Artificial Intelligence for Secure Data Communication in Energy-Constrained Healthcare Devices.

Computational intelligence and neuroscience·2022
Same author

Applications of Intelligent Model to Analyze the Green Finance for Environmental Development in the Context of Artificial Intelligence.

Computational intelligence and neuroscience·2022

相关实验视频

Updated: Jul 13, 2025

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.9K

跨口吃:一种基于变压器的深度学习方法,用于使用2D Mel-Spectrogram可视化和基于注意力的特征表示来分类口吃的语言.

Krishna Basak1, Nilamadhab Mishra1, Hsien-Tsung Chang2,3,4,5

  • 1School of Computing Science & Engineering, VIT Bhopal University, Sehore 466114, India.

Sensors (Basel, Switzerland)
|October 14, 2023
PubMed
概括

一个新的深度学习模型,TranStutter,使用先进的注意力机制准确地分类口吃类型. 这项技术在神经发育研究中为语音失调提供了改进的诊断.

关键词:
梅尔-光谱图 (Mel-Spectrogram) 是一个光谱图.多头自我注意的多头自动注意.语言不流利 语言不流利自语的语言自语.变压器的变压器是一个变压器.

更多相关视频

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.5K
Utilizing Repetitive Transcranial Magnetic Stimulation to Improve Language Function in Stroke Patients with Chronic Non-fluent Aphasia
10:15

Utilizing Repetitive Transcranial Magnetic Stimulation to Improve Language Function in Stroke Patients with Chronic Non-fluent Aphasia

Published on: July 2, 2013

17.9K

相关实验视频

Last Updated: Jul 13, 2025

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.9K
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.5K
Utilizing Repetitive Transcranial Magnetic Stimulation to Improve Language Function in Stroke Patients with Chronic Non-fluent Aphasia
10:15

Utilizing Repetitive Transcranial Magnetic Stimulation to Improve Language Function in Stroke Patients with Chronic Non-fluent Aphasia

Published on: July 2, 2013

17.9K

科学领域:

  • 语言病理学 语音病理学
  • 神经发育障碍 神经发育障碍
  • 医疗保健中的人工智能

背景情况:

  • 吃是一种常见的神经发育障碍,影响言语流.
  • 准确的对口吃类型的分类对于有效的诊断和干预至关重要.
  • 现有的方法可能无法完全捕捉到语言不流的复杂时间模式.

研究的目的:

  • 介绍TranStutter,一种基于变压器的新型深度学习模型,用于语音不流利的分类.
  • 为了评估TranStutter在识别各种口吃类型的准确性.
  • 为了证明模型的潜力,以提高口吃的诊断和治疗.

主要方法:

  • 开发了TranStutter,这是一个使用多头自我注意和定位编码的深度学习模型.
  • 在两个基准数据集上测试了TranStutter:播客中的口吃事件 (SEP-28k) 和FluencyBank采访子集.
  • 基于不同口吃亚型 (阻塞,延长,重复,插入) 的分类准确度评估模型性能.

主要成果:

  • 在SEP-28k数据集上,TranStutter取得了88.1%的准确性.
  • 该模型在FluencyBank数据集上显示了80.6%的准确性.
  • 结果表明,在捕捉复杂的时间语音模式方面,性能优越.

结论:

  • "TranStutter"显示了彻底改变口吃的诊断和治疗的巨大潜力.
  • 该模型的创新架构可以精确识别细微的失调.
  • 这一进步有助于针对性干预的语言病理学和神经发育研究.