Time-frequency analysis of speech signals using the Stockwell transform for the detection of upper respiratory tract infection

IF 3.4 2区物理与天体物理 Q1 ACOUSTICS

Applied Acoustics Pub Date : 2024-10-16 DOI:10.1016/j.apacoust.2024.110339

Pankaj Warule , Siba Prasad Mishra , Suman Deb , Jarek Krajewski

{"title":"Time-frequency analysis of speech signals using the Stockwell transform for the detection of upper respiratory tract infection","authors":"Pankaj Warule , Siba Prasad Mishra , Suman Deb , Jarek Krajewski","doi":"10.1016/j.apacoust.2024.110339","DOIUrl":null,"url":null,"abstract":"<div><div>The acoustic properties of speech demonstrate modifications in the presence of different health states. Biomedical engineering has great promise for creating non-invasive diagnostic processes that use speech as a biomarker. The use of speech indications to screen for upper respiratory tract infections (URTIs), such as the common cold, may have potential advantages in terms of limiting transmission. In this study, we have employed the Stockwell transform -based time-frequency (TF) analysis of speech signals for URTI detection. The Stockwell transform is applied on speech signals to derive their TF representation. Using a TF matrix, the various statistics of magnitude and phase are calculated and used as features for classifying speech of healthy speakers and speakers with URTI. The URTIC database is employed for evaluating the proposed features. The utilization of an ensemble of support vector machines (SVM) is proposed as a classification approach to address the issue of class imbalance. The results show that the proposed method produces comparable outcomes to state-of-the-art approaches. The proposed features obtain 66.53% and 64.65% UARs on the development and test partitions of the URTIC database.</div></div>","PeriodicalId":55506,"journal":{"name":"Applied Acoustics","volume":null,"pages":null},"PeriodicalIF":3.4000,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Applied Acoustics","FirstCategoryId":"101","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0003682X24004900","RegionNum":2,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ACOUSTICS","Score":null,"Total":0}

引用次数: 0

Abstract

The acoustic properties of speech demonstrate modifications in the presence of different health states. Biomedical engineering has great promise for creating non-invasive diagnostic processes that use speech as a biomarker. The use of speech indications to screen for upper respiratory tract infections (URTIs), such as the common cold, may have potential advantages in terms of limiting transmission. In this study, we have employed the Stockwell transform -based time-frequency (TF) analysis of speech signals for URTI detection. The Stockwell transform is applied on speech signals to derive their TF representation. Using a TF matrix, the various statistics of magnitude and phase are calculated and used as features for classifying speech of healthy speakers and speakers with URTI. The URTIC database is employed for evaluating the proposed features. The utilization of an ensemble of support vector machines (SVM) is proposed as a classification approach to address the issue of class imbalance. The results show that the proposed method produces comparable outcomes to state-of-the-art approaches. The proposed features obtain 66.53% and 64.65% UARs on the development and test partitions of the URTIC database.

查看原文本刊更多论文

利用斯托克韦尔变换对语音信号进行时频分析以检测上呼吸道感染

在不同的健康状况下，语音的声学特性会发生变化。生物医学工程有望创造出利用语音作为生物标记的非侵入性诊断程序。利用语音指示来筛查上呼吸道感染（URTI），如普通感冒，在限制传播方面可能具有潜在的优势。在这项研究中，我们采用了基于斯托克韦尔变换的时频（TF）分析，对语音信号进行 URTI 检测。斯托克韦尔变换应用于语音信号，以得出其 TF 表示。通过 TF 矩阵，可以计算出幅度和相位的各种统计量，并将其作为特征对健康说话者和 URTI 说话者的语音进行分类。URTIC 数据库用于评估所提出的特征。建议使用支持向量机（SVM）集合作为分类方法，以解决类别不平衡的问题。结果表明，所提出的方法产生的结果与最先进的方法相当。所提出的特征在 URTIC 数据库的开发分区和测试分区上分别获得了 66.53% 和 64.65% 的 UAR。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Applied Acoustics 物理-声学

CiteScore

7.40

自引率

11.80%

发文量

618

审稿时长

7.5 months

期刊介绍： Since its launch in 1968, Applied Acoustics has been publishing high quality research papers providing state-of-the-art coverage of research findings for engineers and scientists involved in applications of acoustics in the widest sense. Applied Acoustics looks not only at recent developments in the understanding of acoustics but also at ways of exploiting that understanding. The Journal aims to encourage the exchange of practical experience through publication and in so doing creates a fund of technological information that can be used for solving related problems. The presentation of information in graphical or tabular form is especially encouraged. If a report of a mathematical development is a necessary part of a paper it is important to ensure that it is there only as an integral part of a practical solution to a problem and is supported by data. Applied Acoustics encourages the exchange of practical experience in the following ways: • Complete Papers • Short Technical Notes • Review Articles; and thereby provides a wealth of technological information that can be used to solve related problems. Manuscripts that address all fields of applications of acoustics ranging from medicine and NDT to the environment and buildings are welcome.