[论文解读] Studying the Similarity of COVID-19 Sounds based on Correlation Analysis of MFCC

Mohamed Bader, Ismail Shahin+1 more|arXiv (Cornell University)|Oct 17, 2020

Music and Audio Processing参考文献 13被引用 6

一句话总结

本研究利用梅尔频率倒谱系数（MFCCs）和皮尔逊相关性分析，调查了与COVID-19相关的咳嗽声和呼吸声的声学相似性。研究发现，COVID-19患者的咳嗽声和呼吸声样本在MFCC上表现出高度相似性，而语音样本在区分COVID-19与非COVID-19病例方面展现出更强的鲁棒性，表明基于语音的筛查方法可能减少对这些信号的进一步处理需求。

ABSTRACT

Recently there has been a formidable work which has been put up from the people who are working in the frontlines such as hospitals, clinics, and labs alongside researchers and scientists who are also putting tremendous efforts in the fight against COVID-19 pandemic. Due to the preposterous spread of the virus, the integration of the artificial intelligence has taken a considerable part in the health sector, by implementing the fundamentals of Automatic Speech Recognition (ASR) and deep learning algorithms. In this paper, we illustrate the importance of speech signal processing in the extraction of the Mel-Frequency Cepstral Coefficients (MFCCs) of the COVID-19 and non-COVID-19 samples and find their relationship using Pearson correlation coefficients. Our results show high similarity in MFCCs between different COVID-19 cough and breathing sounds, while MFCC of voice is more robust between COVID-19 and non-COVID-19 samples. Moreover, our results are preliminary, and there is a possibility to exclude the voices of COVID-19 patients from further processing in diagnosing the disease.

研究动机与目标

• 利用MFCC评估与COVID-19相关的声学相似性。
• 评估MFCC在区分COVID-19与非COVID-19发声中的判别能力。
• 探讨是否可因COVID-19患者语音样本中MFCC模式的鲁棒性，而将其从进一步的诊断处理中排除。
• 研究基于MFCC相关性分析实现无创、人工智能辅助检测COVID-19的可行性。

提出的方法

• 从COVID-19患者和非COVID-19个体的咳嗽声、呼吸声及语音样本中提取MFCC。
• 应用皮尔逊相关系数分析，比较不同声学类型和群体之间的MFCC向量。
• 对比组内相似性（如所有COVID-19咳嗽声）与组间相似性（如COVID-19咳嗽声与非COVID-19语音的对比）。
• 使用从患者和对照组收集的音频记录数据集，重点关注呼吸声和语音。
• 评估MFCC表征在不同声学模态（咳嗽、呼吸、语音）中的鲁棒性。

实验结果

研究问题

• RQ1 COVID-19患者之间的咳嗽声和呼吸声MFCC表征有多相似？
• RQ2 COVID-19患者语音样本的MFCC与非COVID-19患者语音样本相比如何？
• RQ3 能否利用COVID-19呼吸声中MFCC的高相关性实现疾病检测？
• RQ4 语音的MFCC表征在区分COVID-19与非COVID-19病例方面是否更具鲁棒性？

主要发现

• 在不同COVID-19咳嗽声和呼吸声样本之间观察到MFCC的高相关性，表明组内相似性显著。
• 与非COVID-19语音相比，COVID-19患者语音样本的MFCC表现出更高的鲁棒性和独特性。
• 本研究建议，由于MFCC模式的一致性，可将COVID-19患者的语音样本从进一步的诊断处理中排除。
• 结果表明，MFCC相关性分析能够有效捕捉呼吸声中具有判别性的特征，适用于潜在的人工智能筛查。