相关实验视频

Updated: May 10, 2025

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

Published on: August 9, 2024

使用机器学习在歌声中的压力自动分类

Yuanyuan Liu¹, Mittapalle Kiran Reddy², Madhu Keerthana Yagnavajjula³

¹Speech and Voice Research Laboratory, Tampere University, Tampere 33100, Finland.

Journal of voice : official journal of the Voice Foundation

|April 19, 2025

概括

机器学习使用声学特征准确地分类歌唱声音应变,帮助声部健康和训练. 这项技术有望保护专业歌手免受过度使用.

科学领域:

声声声学和生物声学
在语音和语音分析中的机器学习应用.
唱歌的声音科学和教学.

背景情况:

分类声应变对于保护专业歌手和优化声乐训练至关重要.
目前用于评估声应变的方法可能是主观的,耗时的.
区分正常-轻度和中度-严重的菌株是干预的关键.

研究的目的:

研究机器学习在基于感知声应变的基础上自动分类歌唱声音的有效性.
为了比较不同声学特征集和机器学习分类器的性能,用于应变检测.
分析来自古典和当代商业音乐 (CCM) 类型的歌声样本.

主要方法:

分析了来自15位专业歌手 (古典和CCM) 的324个歌声样本.
提取和比较三种声学特征集:Mel频 cepstral 系数 (MFCC),扩展的日内瓦极简声学参数集 (eGeMAPS) 和波纹散射特征.
使用支持向量机 (SVM) 和多层感知子 (MLP) 分类器,用于特征选择,具有递归特征消除.

主要成果:

使用波纹散射特征与MLP分类器实现的最高分类准确率为86.1%.
第一个MFCC系数,表示光谱倾斜,证明了菌株类别之间最显著的分离.
选择的声学特征和机器学习模型在区分声应变水平方面被证明是有效的.

结论:

机器学习模型可以自动对高准确度的唱歌声音的感知声应变进行分类.
这种方法有可能支持声乐健康监测和歌唱培训计划.
需要对跨越多种类型的更大,更多样化的歌手群体进行进一步的研究.

关键词:

听觉感知评价支持向量机器多层感知费舍尔向量波纹散射系数半频率切普斯特尔系数

更多相关视频

fMRI Mapping of Brain Activity Associated with the Vocal Production of Consonant and Dissonant Intervals

fMRI Mapping of Brain Activity Associated with the Vocal Production of Consonant and Dissonant Intervals

Published on: May 23, 2017

Author Spotlight: Advancements in the Fabrication of Synthetic Vocal Fold Models for Phonetic and Robotic Applications

Author Spotlight: Advancements in the Fabrication of Synthetic Vocal Fold Models for Phonetic and Robotic Applications

Published on: January 5, 2024

相关概念视频

Measurements of Strain

Measurements of Strain

Strain quantifies the deformation of a material under force, typically measured as normal strain, which represents the change in length when compared with the original length. Electrical strain gauges are used for enhanced accuracy. These devices consist of a conductive wire mounted on a paper backing that adheres to the material's surface. These gauges operate on the piezoresistive effect, where the wire's electrical resistance changes in response to mechanical deformation. The strain...

Classification of Skeletal Muscle Fibers

Classification of Skeletal Muscle Fibers

Skeletal muscles continuously produce ATP to provide the energy that enables muscle contractions. Skeletal muscle fibers can be categorized into three types based on differences in their contraction speed and how they produce ATP, as well as physical differences related to these factors. Most human muscles contain all three muscle fiber types, albeit in varying proportions.
Slow-Twitch Muscle Fibers
Slow oxidative, muscle fibers appear red due to large numbers of capillaries and high levels of...