Acoustic analysis in stuttering: a machine-learning study
BackgroundStuttering is a childhood-onset neurodevelopmental disorder affecting speech fluency. The diagnosis and clinical management of stuttering is currently based on perceptual examination and clinical scales. Standardized techniques for acoustic analysis have prompted promising results for the...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-06-01
|
| Series: | Frontiers in Neurology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fneur.2023.1169707/full |
| _version_ | 1797791263080054784 |
|---|---|
| author | Francesco Asci Francesco Asci Luca Marsili Antonio Suppa Antonio Suppa Giovanni Saggio Elena Michetti Pietro Di Leo Martina Patera Lucia Longo Giovanni Ruoppolo Francesca Del Gado Donatella Tomaiuoli Giovanni Costantini |
| author_facet | Francesco Asci Francesco Asci Luca Marsili Antonio Suppa Antonio Suppa Giovanni Saggio Elena Michetti Pietro Di Leo Martina Patera Lucia Longo Giovanni Ruoppolo Francesca Del Gado Donatella Tomaiuoli Giovanni Costantini |
| author_sort | Francesco Asci |
| collection | DOAJ |
| description | BackgroundStuttering is a childhood-onset neurodevelopmental disorder affecting speech fluency. The diagnosis and clinical management of stuttering is currently based on perceptual examination and clinical scales. Standardized techniques for acoustic analysis have prompted promising results for the objective assessment of dysfluency in people with stuttering (PWS).ObjectiveWe assessed objectively and automatically voice in stuttering, through artificial intelligence (i.e., the support vector machine – SVM classifier). We also investigated the age-related changes affecting voice in stutterers, and verified the relevance of specific speech tasks for the objective and automatic assessment of stuttering.MethodsFifty-three PWS (20 children, 33 younger adults) and 71 age−/gender-matched controls (31 children, 40 younger adults) were recruited. Clinical data were assessed through clinical scales. The voluntary and sustained emission of a vowel and two sentences were recorded through smartphones. Audio samples were analyzed using a dedicated machine-learning algorithm, the SVM to compare PWS and controls, both children and younger adults. The receiver operating characteristic (ROC) curves were calculated for a description of the accuracy, for all comparisons. The likelihood ratio (LR), was calculated for each PWS during all speech tasks, for clinical-instrumental correlations, by using an artificial neural network (ANN).ResultsAcoustic analysis based on machine-learning algorithm objectively and automatically discriminated between the overall cohort of PWS and controls with high accuracy (88%). Also, physiologic ageing crucially influenced stuttering as demonstrated by the high accuracy (92%) of machine-learning analysis when classifying children and younger adults PWS. The diagnostic accuracies achieved by machine-learning analysis were comparable for each speech task. The significant clinical-instrumental correlations between LRs and clinical scales supported the biological plausibility of our findings.ConclusionAcoustic analysis based on artificial intelligence (SVM) represents a reliable tool for the objective and automatic recognition of stuttering and its relationship with physiologic ageing. The accuracy of the automatic classification is high and independent of the speech task. Machine-learning analysis would help clinicians in the objective diagnosis and clinical management of stuttering. The digital collection of audio samples here achieved through smartphones would promote the future application of the technique in a telemedicine context (home environment). |
| first_indexed | 2024-03-13T02:16:20Z |
| format | Article |
| id | doaj.art-b6ba9262d7f1412091e3367419de8f6a |
| institution | Directory Open Access Journal |
| issn | 1664-2295 |
| language | English |
| last_indexed | 2024-03-13T02:16:20Z |
| publishDate | 2023-06-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neurology |
| spelling | doaj.art-b6ba9262d7f1412091e3367419de8f6a2023-06-30T12:57:55ZengFrontiers Media S.A.Frontiers in Neurology1664-22952023-06-011410.3389/fneur.2023.11697071169707Acoustic analysis in stuttering: a machine-learning studyFrancesco Asci0Francesco Asci1Luca Marsili2Antonio Suppa3Antonio Suppa4Giovanni Saggio5Elena Michetti6Pietro Di Leo7Martina Patera8Lucia Longo9Giovanni Ruoppolo10Francesca Del Gado11Donatella Tomaiuoli12Giovanni Costantini13Department of Human Neurosciences, Sapienza University of Rome, Rome, ItalyIRCCS Neuromed Institute, Pozzilli, ItalyDepartment of Neurology, James J. and Joan A. Gardner Center for Parkinson’s Disease and Movement Disorders, University of Cincinnati, Cincinnati, OH, United StatesDepartment of Human Neurosciences, Sapienza University of Rome, Rome, ItalyIRCCS Neuromed Institute, Pozzilli, ItalyDepartment of Electronic Engineering, University of Rome Tor Vergata, Rome, ItalyCRC – Centro Ricerca e Cura, Rome, ItalyDepartment of Electronic Engineering, University of Rome Tor Vergata, Rome, ItalyDepartment of Human Neurosciences, Sapienza University of Rome, Rome, ItalyDepartment of Sense Organs, Otorhinolaryngology Section, Sapienza University of Rome, Rome, ItalyIRCCS San Raffaele Pisana, Rome, ItalyCRC – Centro Ricerca e Cura, Rome, ItalyCRC – Centro Ricerca e Cura, Rome, ItalyDepartment of Electronic Engineering, University of Rome Tor Vergata, Rome, ItalyBackgroundStuttering is a childhood-onset neurodevelopmental disorder affecting speech fluency. The diagnosis and clinical management of stuttering is currently based on perceptual examination and clinical scales. Standardized techniques for acoustic analysis have prompted promising results for the objective assessment of dysfluency in people with stuttering (PWS).ObjectiveWe assessed objectively and automatically voice in stuttering, through artificial intelligence (i.e., the support vector machine – SVM classifier). We also investigated the age-related changes affecting voice in stutterers, and verified the relevance of specific speech tasks for the objective and automatic assessment of stuttering.MethodsFifty-three PWS (20 children, 33 younger adults) and 71 age−/gender-matched controls (31 children, 40 younger adults) were recruited. Clinical data were assessed through clinical scales. The voluntary and sustained emission of a vowel and two sentences were recorded through smartphones. Audio samples were analyzed using a dedicated machine-learning algorithm, the SVM to compare PWS and controls, both children and younger adults. The receiver operating characteristic (ROC) curves were calculated for a description of the accuracy, for all comparisons. The likelihood ratio (LR), was calculated for each PWS during all speech tasks, for clinical-instrumental correlations, by using an artificial neural network (ANN).ResultsAcoustic analysis based on machine-learning algorithm objectively and automatically discriminated between the overall cohort of PWS and controls with high accuracy (88%). Also, physiologic ageing crucially influenced stuttering as demonstrated by the high accuracy (92%) of machine-learning analysis when classifying children and younger adults PWS. The diagnostic accuracies achieved by machine-learning analysis were comparable for each speech task. The significant clinical-instrumental correlations between LRs and clinical scales supported the biological plausibility of our findings.ConclusionAcoustic analysis based on artificial intelligence (SVM) represents a reliable tool for the objective and automatic recognition of stuttering and its relationship with physiologic ageing. The accuracy of the automatic classification is high and independent of the speech task. Machine-learning analysis would help clinicians in the objective diagnosis and clinical management of stuttering. The digital collection of audio samples here achieved through smartphones would promote the future application of the technique in a telemedicine context (home environment).https://www.frontiersin.org/articles/10.3389/fneur.2023.1169707/fullstutteringmachine-learningtelemedicinehome environmentacoustic analysis |
| spellingShingle | Francesco Asci Francesco Asci Luca Marsili Antonio Suppa Antonio Suppa Giovanni Saggio Elena Michetti Pietro Di Leo Martina Patera Lucia Longo Giovanni Ruoppolo Francesca Del Gado Donatella Tomaiuoli Giovanni Costantini Acoustic analysis in stuttering: a machine-learning study Frontiers in Neurology stuttering machine-learning telemedicine home environment acoustic analysis |
| title | Acoustic analysis in stuttering: a machine-learning study |
| title_full | Acoustic analysis in stuttering: a machine-learning study |
| title_fullStr | Acoustic analysis in stuttering: a machine-learning study |
| title_full_unstemmed | Acoustic analysis in stuttering: a machine-learning study |
| title_short | Acoustic analysis in stuttering: a machine-learning study |
| title_sort | acoustic analysis in stuttering a machine learning study |
| topic | stuttering machine-learning telemedicine home environment acoustic analysis |
| url | https://www.frontiersin.org/articles/10.3389/fneur.2023.1169707/full |
| work_keys_str_mv | AT francescoasci acousticanalysisinstutteringamachinelearningstudy AT francescoasci acousticanalysisinstutteringamachinelearningstudy AT lucamarsili acousticanalysisinstutteringamachinelearningstudy AT antoniosuppa acousticanalysisinstutteringamachinelearningstudy AT antoniosuppa acousticanalysisinstutteringamachinelearningstudy AT giovannisaggio acousticanalysisinstutteringamachinelearningstudy AT elenamichetti acousticanalysisinstutteringamachinelearningstudy AT pietrodileo acousticanalysisinstutteringamachinelearningstudy AT martinapatera acousticanalysisinstutteringamachinelearningstudy AT lucialongo acousticanalysisinstutteringamachinelearningstudy AT giovanniruoppolo acousticanalysisinstutteringamachinelearningstudy AT francescadelgado acousticanalysisinstutteringamachinelearningstudy AT donatellatomaiuoli acousticanalysisinstutteringamachinelearningstudy AT giovannicostantini acousticanalysisinstutteringamachinelearningstudy |