解码咳声音中的性别:基于变压器的分析
Linh He1, Haomiao Li2, Siyan Wang2
1Sean Parker Institute for the Voice, Department of Otolaryngology - Head & Neck Surgery, Weill Cornell Medical College, New York, New York, USA.
The Laryngoscope
|January 27, 2026
概括
咳声学包含性别特征,可通过AI模型检测. 这些发现可以通过识别非语音声音差异来帮助性别肯定语音护理.
科学领域:
- 喉腔病理学 喉腔病理学
- 声学分析 声学分析
- 人工智能的人工智能
背景情况:
- 音调和音量等语音特征会影响性别认知.
- 关于性别差异,非语音声音,例如咳,对性别差异的理解较少.
- 这种知识差距影响了性别确认的语音护理,因为咳很难调节.
研究的目的:
- 为了研究咳声音的基于性别的声学差异.
- 使用具有自我注意力的变压器模型来识别用于性别分类的关键咳特征.
主要方法:
- 来自Coswara数据集的327个咳记录 (154名男性,173名女性) 的分析.
- 应用HuBERT变压器模型用于预处理后的音频分析 (重新采样,消除沉默,规范化,修剪).
- 使用标准化平均差异 (SMD) 查验证性别平衡.
主要成果:
- 变压器模型在从咳系列中分类性别时,获得了84.0%的准确率和0.8462的F1得分.
- 仅使用单一咳样本时,分类准确性较低 (71.4%).
- 注意力可视化强调爆炸性咳阶段对于性别区分至关重要.
结论:
- 咳的声音具有性别歧视的声学特征,可通过变压器模型识别.
- 具体的咳阶段包含了生理学上与性别分类相关的信息.
- 调查结果可以为非语音声音制作的性别肯定干预提供信息.
相关概念视频
Socioemotional Experience and Gender Development
277
Social-emotional experiences and cultural influences play significant roles in shaping gender development. During middle childhood, from ages 6 to 11, peer groups become dominant in reinforcing gender norms. Children in this age group often align with same-gender peer groups, which actively encourage behaviors that conform to traditional gender roles. For instance, boys may be discouraged from engaging in activities perceived as feminine, reinforcing culturally dictated norms about masculinity...
277
Soundness of Cement
559
The soundness of cement refers to the ability of cement paste to retain its volume after setting. Unsound cement can lead to expansion and structural damage due to the presence of free lime, magnesia, and calcium sulfate. Free lime hydrates very slowly, expanding and causing unsoundness, which is difficult to detect because it intercrystallizes with other compounds. Magnesia also reacts with water, forming crystals that can disrupt the cement's structure. Calcium sulfate can create...
559
Heart Sounds
3.5K
Heart sounds are generated by the turbulence in blood flow due to the closing of heart valves. These sounds are best perceived slightly away from the valves, where the blood flow disseminates the sound.
Auscultation is the process of listening to these internal body sounds using a stethoscope. The heart produces four types of sounds, but only two—S1 and S2—can usually be heard with a stethoscope.
S1, also known as the "lub" sound, is caused by the closure of atrioventricular (A-V)...
Auscultation is the process of listening to these internal body sounds using a stethoscope. The heart produces four types of sounds, but only two—S1 and S2—can usually be heard with a stethoscope.
S1, also known as the "lub" sound, is caused by the closure of atrioventricular (A-V)...
3.5K
Korotkoff Sounds
7.9K
Korotkoff sounds are the specific sounds heard while measuring blood pressure using a sphygmomanometer, typically with a stethoscope or a Doppler device. They are named after Russian physician Nikolai Korotkov, who first described them in 1905. These sounds correspond to turbulent blood flow in the artery as the blood pressure cuff is gradually released after inflation.
During blood pressure assessment, inflating the cuff 30 millimeters of mercury above the patient's systolic blood pressure...
During blood pressure assessment, inflating the cuff 30 millimeters of mercury above the patient's systolic blood pressure...
7.9K
Sound Waves
12.9K
Sound waves can be thought of as fluctuations in the pressure of a medium through which they propagate. Since the pressure also makes the medium's particles vibrate along its direction of motion, the waves can be modeled as the displacement of the medium's particles from their mean position.
Sound waves are longitudinal in most fluids because fluids cannot sustain any lateral pressure. In solids, however, shear forces help in propagating the disturbance in the lateral direction as well....
Sound waves are longitudinal in most fluids because fluids cannot sustain any lateral pressure. In solids, however, shear forces help in propagating the disturbance in the lateral direction as well....
12.9K
Sound Intensity
4.8K
The loudness of a sound source is related to how energetically the source is vibrating, consequently making the molecules of the propagation medium vibrate. To measure the loudness of a source, the physical quantity of interest is the intensity. This is defined as the energy emitted per unit of time per unit of area perpendicular to the sound wave's propagation direction. Since the total energy is greater if the source vibrates for a longer duration and over a larger area, dividing the...
4.8K


