不同品牌智能手机语音采集的一致性及其临床可行性研究

Study on the consistency of voice collection across different smartphone brands and its clinical usability

郑家兴;陈凯文;汤雨婷;王刚;徐韵婷;欧建林;黄译萱;凌卫新;陈卓铭

1:暨南大学附属第一医院康复医学科

2:华南理工大学数学学院

3:广州卫生职业技术学院康复保健学院

摘要
目的 比较国内常用品牌智能手机与专业录音设备采录的语音参数的差异,探究智能手机是否可应用于临床语音研究。方法 选取67例正常受试者,分别使用6种不同品牌智能手机(登录国家重点研发计划“主动康健”筛查小程序)和专业录音设备进行语音采集,提取元音/a/、/i/、/u/基频类、频率类、振幅类、共振峰类、能量类等语音声学参数,采用单因素ANOVA检验和Tukey's HSD对变量进行两两比较。结果 6种不同品牌智能手机与专业录音设备之间基频类:Median F0、Mean F0、Max F0、Min F0,频率类:jitter local、jitter local absolute、jitter rap、jitter ppq5、jitter ddp,振幅类:shimmer local、shimmer local dB、shimmer apq3、shimmer apq5、shimmer apq11、shimmer dda,共振峰类:F1、F2、F3、F4语音声学参数无显著性差异(均为P>0.05);能量类参数:mean energy(F=31.171,P<0.001)、max energy(F=34.193,P<0.001)、min energy(F=5.453,P<0.001)存在显著性差异。结论 国内常用智能手机通过国家重点研发计划“主动康健”筛查小程序录音可以代替专业录音设备进行语音研究,但在选取语音声学参数时能量类参数应当谨慎考虑。
关键词
智能手机;能量;语音参数;元音;专业录音设备
基金项目(Foundation):
国家重点研发计划(2020YFC2005700)
作者
郑家兴;陈凯文;汤雨婷;王刚;徐韵婷;欧建林;黄译萱;凌卫新;陈卓铭
参考文献

[1] IDRISOGLU A,DALLORA A,ANDERBERG P,et al.Applied machine learning techniques to diagnose voice-affecting conditions and disorders:systematic literature review[J].Journal of Medical Internet Research,2023,25e46105-e46105,25.DOI:10.2196/46105.

[2] KIM H B,SNG J,PARK S,et al.Classification of laryngeal diseases including laryngeal cancer,benign mucosal disease,and vocal cord paralysis by artificial intelligence using voice analysis[J].Scientific Reports,2024,14(1):9297-9297.

[3] BRINGEL A K,LEONE C D,FIRMINO C D L V J,et al.Voice analysis and neural networks as a clinical decision support system for patients with lung diseases[J].Mayo Clinic Proceedings:Digital Health,2024,2(3):367-374.

[4] GIOVANNI C,VALERIO C,PIETRO L D,et al.Artificial intelligence-based voice assessment of patients with Parkinson's disease off and on treatment:machine vs.deep-learning comparison[J].Sensors,2023,23(4):2293-2293.

[5] HE T,CHEN J,XU X,et al.Exploiting smartphone voice recording as a digital biomarker for Parkinson's disease diagnosis[J].IEEE Transactions on Instrumentation and Measurement,73[2024-09-09].DOI:10.1109/TIM.2024.3391339.

[6] LIN E,HORNIBROOK J,ORMOND T.Evaluating iPhone recordings for acoustic voice assessment[J].Folia Phoniatr Logop,2012,64(3):122-130.

[7] 孙宇欣,姚权,KIM H K,等.国产智能手机测试基频的可能性及其影响因素[J].听力学及言语疾病杂志,2022,30(5):504-507.

[8] BOTTALICO P,CODINO J,CANTOR-CUTIVA C L,et al.Reproducibility of voice parameters:the effect of room acoustics and microphones[J].J Voice,2020,34(3):320-334.

[9] KAUFMAN J M,ANIRUDH T,YAN F.Acoustic analysis and prediction of type 2 diabetes mellitus using smartphone-recorded voice segments[J].Mayo Clinic Procee-dings:Digital Health,2023,1(4):534-544.

[10] TRACY M J,?ZKANCA Y,ATKINS C D,et al.Investigating voice as a biomarker:deep phenotyping methods for early detection of Parkinson's disease[J].Journal of Biomedical Informatics,2020,104103362.DOI:10.1016/j.jbi.2019.103362

[11] VIRGINIE R,KATHY H,BERNARD H,et al.Vowel production:a potential speech biomarker for early detection of dysarthria in Parkinson's disease[J].Frontiers in Psychology,2023,141129830-1129830.DOI:10.3389/FPSYG.2023.1129830

[12] WANG M,ZHAO X,LI F,et al.Using sustained vowels to identify patients with mild Parkinson's disease in a Chinese dataset[J].Frontiers in Aging Neuroscience,2024,161377442-1377442.DOI:10.3389/FNAGI.2024.1377442

[13] LIU S.Analyzing consumer behavior and brand loyalty in the Chinese smartphone market:a case study of Huawei[J].Frontiers in Management Science,2024,3(3):35-42.

[14] CHRISTEL G,ANDREA M R,FEDERICO V,et al.Acoustic analysis of normal voice patterns in Italian adults by using Praat[J].J Voice,2020,34(6):961.e9-961.e18.

[15] ONEN C,GOLAC H,SONGUR E T,et al.Acoustic and auditory-perceptual analysis of voice in the female smokers who do not have self-reported voice complaint[J].J Voice,2023,37(2):297.e1-297.e6.DOI:10.1016/j.jvoice.2020.12.050.

[16] MARSANO-CORNEJO M J,áNGEL R.Comparison of the acoustic parameters obtained with different smartphones and a professional microphone[J].Acta Otorrinolaringologica Espanola,2022,73(1):51-55.

[17] ASHISH K,ARATHY V,DHEERAJ K,et al.MEMS-based piezoresistive and capacitive microphones:a review on materials and methods[J].Materials Science in Semiconductor Processing,2024,169.DOI:10.1016/J.MSSP.2023.107879

[18] SUJATHA C.Equipment for measurements in acoustics[M].Vibration,Acoustics and Strain Measurement:Theory and Experiments.Cham:Springer International Publishing,2023:219-273.

[19] BROCKMANN-BAUSER M,DE PAULA SOARES M F.Do we get what we need from clinical acoustic voice mea-surements?[J].Applied Sciences,2023,13(2):941.DOI:10.3390/app13020941.

[20] FLORENCIO V D O,ALMEIDA A,BALATA P,et al.Differences and reliability of linear and nonlinear acoustic measures as a function of vocal intensity in individuals with voice disorders[J].J Voice,2023,37(5):663-681.

[21] PETRIZZO D,POPOLO P S.Smartphone use in clinical voice recording and acoustic analysis:a literature review-science direct[J].J Voice,2021,35(3):499.e23-499.e28.DOI:10.1016/j.jvoice.2019.10.006.