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

Integration by Parts: Problem Solving01:29

Integration by Parts: Problem Solving

211
Smart speakers process voice commands by modeling audio inputs as piecewise functions and analyzing them through integration against trigonometric functions, such as cosine. This mathematical approach is fundamental in signal processing, where complex sound waves are decomposed into simpler frequency components.Consider a definite integral involving a piecewise function multiplied by a cosine function. Because the function is defined differently over separate intervals, the integral is split...
211

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

Large Language Models Reveal the Neural Tracking of Linguistic Context in Attended and Unattended Multi-Talker Speech.

bioRxiv : the preprint server for biology·2026
Same author

Large language models reveal the neural tracking of linguistic context in attended and unattended multi-talker speech.

Imaging neuroscience (Cambridge, Mass.)·2026
Same author

Real-time brain-controlled selective hearing enhances speech perception in multi-talker environments.

Nature neuroscience·2026
Same author

From Selective Listening to Brain-Controlled Hearing: A Perspective on the Future of Auditory Technology.

Journal of the Association for Research in Otolaryngology : JARO·2026
Same author

Convolutional neural network models describe the encoding subspace of local circuits in auditory cortex.

Nature neuroscience·2026
Same author

Speaker Identity is Robustly Encoded in Spatial Patterns of Intracranial EEG for Attention Decoding.

bioRxiv : the preprint server for biology·2025

相关实验视频

Updated: May 5, 2026

A Method for Tracking the Time Evolution of Steady-State Evoked Potentials
12:03

A Method for Tracking the Time Evolution of Steady-State Evoked Potentials

Published on: May 25, 2019

8.4K

了解深度语音识别系统中的适应性,多尺度的时间集成.

Menoua Keshishian1, Sam V Norman-Haignere1, Nima Mesgarani1

  • 1Department of Electrical Engineering, Zuckerman Mind Brain Behavior Institute, Columbia University, New York, NY 10027.

Advances in neural information processing systems
|May 13, 2024
PubMed
概括
此摘要是机器生成的。

深度神经网络 (DNN) 通过整合跨不同时间尺度的信息来学习语音. 这项研究揭示了DNN中的层次结构,早期层使用时间束集成,后来的层使用结构束集成.

更多相关视频

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

441
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

相关实验视频

Last Updated: May 5, 2026

A Method for Tracking the Time Evolution of Steady-State Evoked Potentials
12:03

A Method for Tracking the Time Evolution of Steady-State Evoked Potentials

Published on: May 25, 2019

8.4K
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

441
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

科学领域:

  • 计算神经科学是一种计算神经科学.
  • 机器学习是机器学习.
  • 语音处理 语音处理

背景情况:

  • 自然语音信号在多个时间尺度上表现出层次结构.
  • 深度神经网络 (DNN) 在模式识别方面是有效的,但它们的时间整合机制尚未得到充分理解.

研究的目的:

  • 用时间上下文不变 (TCI) 范式研究DNN中的时间整合.
  • 了解DNN,特别是DeepSpeech2,如何在不同的时间尺度上处理语音.

主要方法:

  • 应用TCI范式来测量DNN单位中的时间整合窗口.
  • 分析了不同背景下对刺激部分的反应.
  • 研究了培训期间的整合窗口变化以及时间延长/压缩的语音.

主要成果:

  • 大多数DNN单元都具有紧的集成窗口.
  • 培训导致早期层缩小集成窗口,并在后期层扩大窗口,形成层次结构.
  • 确定了一个过渡点,即集成窗口变得结构约束 (例如语音持续时间),而不是绝对时间依赖.
  • 在循环和卷积网络中观察到类似的现象,在循环网络中结构约束集成更为突出.

结论:

  • 语音编码的DNN采用一个层次的模式:早期层的短,时间束的窗口和后来的层的长,结构束的窗口.
  • TCI范式为分析复杂机器学习模型中的时间集成提供了一种多功能工具.