检查高频信息对对话产生的英语摩擦词的分类的影响
Viktor Kharlamov1, Daniel Brenner2, Benjamin V Tucker3
1Department of Languages, Linguistics, and Comparative Literature, Florida Atlantic University, Boca Raton, Florida 33431, USA.
The Journal of the Acoustical Society of America
|September 27, 2023
概括
8kHz以上的高频声音不会在随机森林模型中改善对话语音摩擦分类. 然而,包括这些更高的频率改变了特定的频谱测量对语音分析的重要性.
科学领域:
- 声学 声学 在声学方面
- 语言学的语言学.
- 机器学习 机器学习
背景情况:
- 折辅音分类通常依赖于低于8kHz的光谱测量.
- 高频率 (>8 kHz) 在分类对话语音摩擦的作用仍未得到充分研究,特别是在非实验室环境中.
研究的目的:
- 通过随机森林建模,研究高频信息 (>8 kHz) 对对话语音摩擦的分类准确度的影响.
- 为了比较不同的光谱和振幅测量在语音声音分析中的贡献.
主要方法:
- 利用了西加拿大英语社会语言面试录音的集体,采用了44.1和16kHz的样本.
- 分析了使用福里埃分析和多步法进行的光谱测量.
- 随机森林模型与高频信息和振幅指标的随机森林模型进行比较.
主要成果:
- 8kHz以上的频率信息没有提高摩擦物的整体分类准确性.
- 纳入更高的频率改变了光谱测量的相对重要性,在更高的采样率下降了"重心",增加了"光谱标准偏差".
- 在里埃和多级分类方法之间没有观察到显著的分类精度差异.
- 增加功率测量提高了模型的准确性,但没有改变光谱测量的主导地位.
结论:
- 高频谱信息 (>8 kHz) 并不能显著改善随机森林对对话语音摩擦的分类.
- 该分析强调了不同频率范围和声学测量在语音声征的细微贡献.
- 里埃法和多步法都可用于此类分类任务,功率测量提供额外的好处.
相关概念视频
01:21Perceiving Loudness, Pitch, and Location
233
The human brain perceives pitch through two primary mechanisms reflected in place theory and frequency theory. Each mechanism describes how sound waves are interpreted as specific pitches by the brain, offering insights into the intricate processes of auditory perception.
Place theory, or place coding, suggests that different pitches are heard because various sound waves activate specific locations along the cochlea's basilar membrane. The brain determines the pitch of a sound by...
Place theory, or place coding, suggests that different pitches are heard because various sound waves activate specific locations along the cochlea's basilar membrane. The brain determines the pitch of a sound by...
233
01:08Determination of Expected Frequency
2.2K
Suppose one wants to test independence between the two variables of a contingency table. The values in the table constitute the observed frequencies of the dataset. But how does one determine the expected frequency of the dataset? One of the important assumptions is that the two variables are independent, which means the variables do not influence each other. For independent variables, the statistical probability of any event involving both variables is calculated by multiplying the individual...
2.2K
01:30Classification of Signals
505
In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
505
01:19Expected Frequencies in Goodness-of-Fit Tests
2.6K
A goodness-of-fit test is conducted to determine whether the observed frequency values are statistically similar to the frequencies expected for the dataset. Suppose the expected frequencies for a dataset are equal such as when predicting the frequency of any number appearing when casting a die. In that case, the expected frequency is the ratio of the total number of observations (n) to the number of categories (k).
2.6K
01:05Doppler Effect - II
3.4K
The Doppler effect has several practical, real-world applications. For instance, meteorologists use Doppler radars to interpret weather events based on the Doppler effect. Typically, a transmitter emits radio waves at a specific frequency toward the sky from a weather station. The radio waves bounce off the clouds and precipitation and travel back to the weather station. The radio frequency of the waves reflected back to the station appears to decrease if the clouds or precipitation are moving...
3.4K