评估延续措施的一致性:神经网络的后置概率,强度速度和持续时间
Kevin Tang1,2, Ratree Wayland2, Fenqi Wang3
1Department of English Language and Linguistics, Institute of English and American Studies, Faculty of Arts and Humanities, Heinrich Heine University Düsseldorf, Düsseldorf, 40225, Germany.
The Journal of the Acoustical Society of America
|August 27, 2024
概括
这项研究评估了阿根廷西班牙语的语音使用声学和语音测量. 语音特征概率 (phonological feature probabilities) 提供了一致的预测,这表明它对测量语音衰减的有效性.
科学领域:
- 语音学 语音学 语音学
- 计算语言学 计算语言学
- 西班牙语方言学 西班牙语方言学
背景情况:
- 联音,即辅音的减弱,是一种常见的语音过程.
- 了解西班牙方言中的 lenition 对于语言分析至关重要.
- 传统的声学测量提供了洞察力,但可能不一致.
研究的目的:
- 为了评估反复的神经网络 (Phonet) 测量用于预测阿根廷西班牙语辅音变音的有效性.
- 为了将Phonet的预测与传统的声学测量进行比较.
- 为了提高Phonet的可访问性,以促进未来的研究.
主要方法:
- 在阿根廷西班牙语的语料库中分析无声和发声的停止.
- 应用三个声学指标:强度,速度和持续时间.
- 两种Phonet测量的利用:声音和连续声学特征的后面概率.
主要成果:
- 声学测量产生了混合和不一致的预测.
- 语音测量总是根据已知的语言因素 (发音,发音位置,上下文) 一致地预测语音.
- 语音测试 (Phonet) 证明是有效的,可靠的方法来测量语音听力.
结论:
- Phonet提供了一种强大而一致的方法来量化辅音变音.
- 这项研究证实Phonet在语音和方言学研究中是一个有价值的工具.
- 发布的资源 (西班牙语Phonet模型,培训管道) 促进了Phonet的更广泛的采用.
更多相关视频
相关概念视频
Long-term Potentiation
Long-term potentiation, or LTP, is one of the ways by which synaptic plasticity—changes in the strength of chemical synapses—can occur in the brain. LTP is the process of synaptic strengthening that occurs over time between pre- and postsynaptic neuronal connections. The synaptic strengthening of LTP works in opposition to the synaptic weakening of long-term depression (LTD) and together are the main mechanisms that underlie learning and memory.
Long-term Potentiation
Long-term potentiation, or LTP, is one of the ways by which synaptic plasticity—changes in the strength of chemical synapses—can occur in the brain. LTP is the process of synaptic strengthening that occurs over time between pre and postsynaptic neuronal connections. The synaptic strengthening of LTP works in opposition to the synaptic weakening of long-term depression (LTD) and together are the main mechanisms that underlie learning and memory.
Hebbian LTP
LTP can occur when presynaptic neurons...
Hebbian LTP
LTP can occur when presynaptic neurons...


