Near-ear sound pressure level distribution in everyday life considering the user’s own voice and privacy

IF 1 3区物理与天体物理 Q4 ACOUSTICS

Acta Acustica Pub Date : 2022-01-01 DOI:10.1051/aacus/2022035

Jule Pohlhausen, I. Holube, J. Bitzer

{"title":"Near-ear sound pressure level distribution in everyday life considering the user’s own voice and privacy","authors":"Jule Pohlhausen, I. Holube, J. Bitzer","doi":"10.1051/aacus/2022035","DOIUrl":null,"url":null,"abstract":"Recently, exploring acoustic conditions of people in their everyday environments has drawn a lot of attention. One of the most important and disturbing sound sources is the test participant’s own voice. This contribution proposes an algorithm to determine the own-voice audio segments (OVS) for blocks of 125 ms and a method for measuring sound pressure levels (SPL) without violating privacy laws. The own voice detection (OVD) algorithm here developed is based on a machine learning algorithm and a set of acoustic features that do not allow for speech reconstruction. A manually labeled real-world recording of one full day showed reliable and robust detection results. Moreover, the OVD algorithm was applied to 13 near-ear recordings of hearing-impaired participants in an ecological momentary assessment (EMA) study. The analysis shows that the grand mean percentage of predicted OVS during one day was approx. 10% which corresponds well to other published data. These OVS had a small impact on the median SPL over all data. However, for short analysis intervals, significant differences up to 30 dB occurred in the measured SPL, depending on the proportion of OVS and the SPL of the background noise.","PeriodicalId":48486,"journal":{"name":"Acta Acustica","volume":"6 1","pages":""},"PeriodicalIF":1.0000,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Acta Acustica","FirstCategoryId":"101","ListUrlMain":"https://doi.org/10.1051/aacus/2022035","RegionNum":3,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"ACOUSTICS","Score":null,"Total":0}

引用次数: 0

Abstract

Recently, exploring acoustic conditions of people in their everyday environments has drawn a lot of attention. One of the most important and disturbing sound sources is the test participant’s own voice. This contribution proposes an algorithm to determine the own-voice audio segments (OVS) for blocks of 125 ms and a method for measuring sound pressure levels (SPL) without violating privacy laws. The own voice detection (OVD) algorithm here developed is based on a machine learning algorithm and a set of acoustic features that do not allow for speech reconstruction. A manually labeled real-world recording of one full day showed reliable and robust detection results. Moreover, the OVD algorithm was applied to 13 near-ear recordings of hearing-impaired participants in an ecological momentary assessment (EMA) study. The analysis shows that the grand mean percentage of predicted OVS during one day was approx. 10% which corresponds well to other published data. These OVS had a small impact on the median SPL over all data. However, for short analysis intervals, significant differences up to 30 dB occurred in the measured SPL, depending on the proportion of OVS and the SPL of the background noise.

查看原文本刊更多论文

近耳声压级分布在日常生活中考虑到用户自己的声音和隐私

最近，探索人们在日常环境中的声学状况引起了人们的广泛关注。最重要和最令人不安的声源之一是测试参与者自己的声音。该贡献提出了一种算法来确定125 ms块的自语音音频段(OVS)和一种测量声压级(SPL)而不违反隐私法的方法。这里开发的自己的语音检测(OVD)算法是基于机器学习算法和一组不允许语音重建的声学特征。手动标记的一天真实世界记录显示可靠和稳健的检测结果。此外，在一项生态瞬时评估(EMA)研究中，将OVD算法应用于13名听力受损参与者的近耳录音。分析表明，预测的OVS在一天内的大平均百分比约为。10%，这与其他公布的数据很吻合。这些OVS对所有数据的中位SPL影响很小。然而，在较短的分析间隔内，根据OVS的比例和背景噪声的SPL，测量到的SPL存在高达30 dB的显著差异。

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

Acta Acustica ACOUSTICS-

CiteScore

2.80

自引率

21.40%

发文量

审稿时长

12 weeks

期刊介绍： Acta Acustica, the Journal of the European Acoustics Association (EAA). After the publication of its Journal Acta Acustica from 1993 to 1995, the EAA published Acta Acustica united with Acustica from 1996 to 2019. From 2020, the EAA decided to publish a journal in full Open Access. See Article Processing charges. Acta Acustica reports on original scientific research in acoustics and on engineering applications. The journal considers review papers, scientific papers, technical and applied papers, short communications, letters to the editor. From time to time, special issues and review articles are also published. For book reviews or doctoral thesis abstracts, please contact the Editor in Chief.