相关实验视频
Updated: Feb 12, 2026
13:19
Deep Neural Networks for Image-Based Dietary Assessment
Published on: March 13, 2021
10.0K
深度神经网络如何看待英语单词中的词汇压力?
Itai Allouche1, Itay Asael1, Rotem Rousso1
1Faculty of Electrical and Computer Engineering, Technion-Israel Institute of Technology, Haifa 3200003, Israel.
The Journal of the Acoustical Society of America
|February 11, 2026
概括
这项研究使用卷积神经网络 (CNN) 预测英语单词中的词汇压力. 这些模型学会了通过分析元音的光谱性质来识别压力,为语音处理提供了深度学习的见解.
科学领域:
- 语音处理 语音处理
- 计算语言学计算语言学
- 机器学习是机器学习.
背景情况:
- 神经网络在语音处理方面很成功,但经常充当黑子.
- 解释神经网络决策对于理解它们的机制至关重要.
- 词汇压力预测是语音和语言研究的一个关键挑战.
研究的目的:
- 研究神经网络在预测词汇压力的决策过程.
- 应用可解释性技术来理解模型如何识别压力模式.
- 探索深度学习模型在英语非字体词中用于压力预测的特征.
主要方法:
- 从阅读和自发言语中构建了英语非字体词汇的数据集.
- 训练了几个卷积神经网络 (CNN) 架构来预测压力位置.
- 使用层层相关性传播 (LRP) 来进行神经网络可解释性分析.
- 进行了特征特定相关性分析,以确定有影响力的声学线索.
主要成果:
- 在预测压力位置方面,CNN的准确性高达92%.
- 层次相关性传播表明,压力和非压力音节,特别是压力元音的光谱性质,影响了预测.
- 表现最好的分类器在很大程度上受到压力元音的第一个和第二个形式的影响,其中包括音调和第三个形式.
- 模型关注的是整个词的信息,而不仅仅是局部的线索.
结论:
- 深度学习模型可以有效地从自然语音数据中学习词汇压力的分布式线索.
- 解释性分析显示,CNN利用特定的声学特征,如形式,用于压力预测.
- 这项工作通过使用自然存在的数据和深度学习可解释性来扩展传统的语音研究.
相关概念视频
02:26Protein Networks
4.6K
An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
4.6K
02:26Protein Networks
2.9K
2.9K
02:18Network Covalent Solids
16.2K
Network covalent solids contain a three-dimensional network of covalently bonded atoms as found in the crystal structures of nonmetals like diamond, graphite, silicon, and some covalent compounds, such as silicon dioxide (sand) and silicon carbide (carborundum, the abrasive on sandpaper). Many minerals have networks of covalent bonds.
To break or to melt a covalent network solid, covalent bonds must be broken. Because covalent bonds are relatively strong, covalent network solids are typically...
To break or to melt a covalent network solid, covalent bonds must be broken. Because covalent bonds are relatively strong, covalent network solids are typically...
16.2K
01:37Neural Regulation
43.5K
Digestion begins with a cephalic phase that prepares the digestive system to receive food. When our brain processes visual or olfactory information about food, it triggers impulses in the cranial nerves innervating the salivary glands and stomach to prepare for food.
43.5K
02:02Responses to Salt Stress
14.7K
Salt stress—which can be triggered by high salt concentrations in a plant’s environment—can significantly affect plant growth and crop production by influencing photosynthesis and the absorption of water and nutrients.
14.7K
02:45Responses to Heat and Cold Stress
14.9K
Every organism has an optimum temperature range within which healthy growth and physiological functioning can occur. At the ends of this range, there will be a minimum and maximum temperature that interrupt biological processes.
14.9K