Nina R Benway, Jonathan L Preston, Asif Salekin, Elaine Hitchcock, Tara McAllister
{"title":"Evaluating acoustic representations and normalization for rhoticity classification in children with speech sound disorders.","authors":"Nina R Benway, Jonathan L Preston, Asif Salekin, Elaine Hitchcock, Tara McAllister","doi":"10.1121/10.0024632","DOIUrl":null,"url":null,"abstract":"<p><p>The effects of different acoustic representations and normalizations were compared for classifiers predicting perception of children's rhotic versus derhotic /ɹ/. Formant and Mel frequency cepstral coefficient (MFCC) representations for 350 speakers were z-standardized, either relative to values in the same utterance or age-and-sex data for typical /ɹ/. Statistical modeling indicated age-and-sex normalization significantly increased classifier performances. Clinically interpretable formants performed similarly to MFCCs and were endorsed for deep neural network engineering, achieving mean test-participant-specific F1-score = 0.81 after personalization and replication (σx = 0.10, med = 0.83, n = 48). Shapley additive explanations analysis indicated the third formant most influenced fully rhotic predictions.</p>","PeriodicalId":73538,"journal":{"name":"JASA express letters","volume":null,"pages":null},"PeriodicalIF":1.2000,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11522988/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"JASA express letters","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1121/10.0024632","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ACOUSTICS","Score":null,"Total":0}
引用次数: 0
Abstract
The effects of different acoustic representations and normalizations were compared for classifiers predicting perception of children's rhotic versus derhotic /ɹ/. Formant and Mel frequency cepstral coefficient (MFCC) representations for 350 speakers were z-standardized, either relative to values in the same utterance or age-and-sex data for typical /ɹ/. Statistical modeling indicated age-and-sex normalization significantly increased classifier performances. Clinically interpretable formants performed similarly to MFCCs and were endorsed for deep neural network engineering, achieving mean test-participant-specific F1-score = 0.81 after personalization and replication (σx = 0.10, med = 0.83, n = 48). Shapley additive explanations analysis indicated the third formant most influenced fully rhotic predictions.