Speech Impairment in Parkinson’s Disease: Acoustic Analysis of Unvoiced Consonants in Italian Native Speakers
The study of the influence of Parkinson’s Disease (PD) on vocal signals has received much attention over the last decades. Increasing interest has been devoted to articulation and acoustic characterization of different phonemes. <bold>Method</bold>: In this study we propose th...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9650872/ |
| _version_ | 1818969580760989696 |
|---|---|
| author | Federica Amato Luigi Borzi Gabriella Olmo Carlo Alberto Artusi Gabriele Imbalzano Leonardo Lopiano |
| author_facet | Federica Amato Luigi Borzi Gabriella Olmo Carlo Alberto Artusi Gabriele Imbalzano Leonardo Lopiano |
| author_sort | Federica Amato |
| collection | DOAJ |
| description | The study of the influence of Parkinson’s Disease (PD) on vocal signals has received much attention over the last decades. Increasing interest has been devoted to articulation and acoustic characterization of different phonemes. <bold>Method</bold>: In this study we propose the analysis of the Transition Regions (TR) of specific phonetic groups to model the loss of motor control and the difficulty to start/stop movements, typical of PD patients. For this purpose, we extracted 60 features from pre-processed vocal signals and used them as input to several machine learning models. We employed two data sets, containing samples from Italian native speakers, for training and testing. The first dataset - 28 PD patients and 22 Healthy Control (HC) - included recordings in optimal conditions, while in the second one - 26 PD patients and 18 HC - signals were collected at home, using non-professional microphones. <bold>Results</bold>: We optimized two support vector machine models for the application in controlled noise conditions and home environments, achieving 98%±1.1 and 88%±2.8 accuracy in 10-fold cross-validation, respectively. <bold>Conclusion</bold>: This study confirms the high capability of the TRs to discriminate between PD patients and healthy controls, and the feasibility of automatic PD assessment using voice recordings. Moreover, the promising performance of the implemented model discloses the option of voice processing using low-cost devices and domestic recordings, possibly self-managed by the patients themselves. |
| first_indexed | 2024-12-20T14:22:51Z |
| format | Article |
| id | doaj.art-d8013550326d4fa7b1b1097fa984f0b8 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-20T14:22:51Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-d8013550326d4fa7b1b1097fa984f0b82022-12-21T19:37:54ZengIEEEIEEE Access2169-35362021-01-01916637016638110.1109/ACCESS.2021.31356269650872Speech Impairment in Parkinson’s Disease: Acoustic Analysis of Unvoiced Consonants in Italian Native SpeakersFederica Amato0https://orcid.org/0000-0003-4409-8794Luigi Borzi1https://orcid.org/0000-0003-0875-6913Gabriella Olmo2https://orcid.org/0000-0002-3670-9412Carlo Alberto Artusi3https://orcid.org/0000-0001-8579-3772Gabriele Imbalzano4Leonardo Lopiano5Department of Computer Engineering, Politecnico di Torino, Torino, ItalyDepartment of Computer Engineering, Politecnico di Torino, Torino, ItalyDepartment of Computer Engineering, Politecnico di Torino, Torino, ItalyDivision of Neurology, A.O.U. Città della Salute e della Scienza di Torino, Turin, ItalyDivision of Neurology, A.O.U. Città della Salute e della Scienza di Torino, Turin, ItalyDivision of Neurology, A.O.U. Città della Salute e della Scienza di Torino, Turin, ItalyThe study of the influence of Parkinson’s Disease (PD) on vocal signals has received much attention over the last decades. Increasing interest has been devoted to articulation and acoustic characterization of different phonemes. <bold>Method</bold>: In this study we propose the analysis of the Transition Regions (TR) of specific phonetic groups to model the loss of motor control and the difficulty to start/stop movements, typical of PD patients. For this purpose, we extracted 60 features from pre-processed vocal signals and used them as input to several machine learning models. We employed two data sets, containing samples from Italian native speakers, for training and testing. The first dataset - 28 PD patients and 22 Healthy Control (HC) - included recordings in optimal conditions, while in the second one - 26 PD patients and 18 HC - signals were collected at home, using non-professional microphones. <bold>Results</bold>: We optimized two support vector machine models for the application in controlled noise conditions and home environments, achieving 98%±1.1 and 88%±2.8 accuracy in 10-fold cross-validation, respectively. <bold>Conclusion</bold>: This study confirms the high capability of the TRs to discriminate between PD patients and healthy controls, and the feasibility of automatic PD assessment using voice recordings. Moreover, the promising performance of the implemented model discloses the option of voice processing using low-cost devices and domestic recordings, possibly self-managed by the patients themselves.https://ieeexplore.ieee.org/document/9650872/Italian native speakersParkinson’s diseasesupport vector machinetele-healthunvoiced consonantsvoice analysis |
| spellingShingle | Federica Amato Luigi Borzi Gabriella Olmo Carlo Alberto Artusi Gabriele Imbalzano Leonardo Lopiano Speech Impairment in Parkinson’s Disease: Acoustic Analysis of Unvoiced Consonants in Italian Native Speakers IEEE Access Italian native speakers Parkinson’s disease support vector machine tele-health unvoiced consonants voice analysis |
| title | Speech Impairment in Parkinson’s Disease: Acoustic Analysis of Unvoiced Consonants in Italian Native Speakers |
| title_full | Speech Impairment in Parkinson’s Disease: Acoustic Analysis of Unvoiced Consonants in Italian Native Speakers |
| title_fullStr | Speech Impairment in Parkinson’s Disease: Acoustic Analysis of Unvoiced Consonants in Italian Native Speakers |
| title_full_unstemmed | Speech Impairment in Parkinson’s Disease: Acoustic Analysis of Unvoiced Consonants in Italian Native Speakers |
| title_short | Speech Impairment in Parkinson’s Disease: Acoustic Analysis of Unvoiced Consonants in Italian Native Speakers |
| title_sort | speech impairment in parkinson x2019 s disease acoustic analysis of unvoiced consonants in italian native speakers |
| topic | Italian native speakers Parkinson’s disease support vector machine tele-health unvoiced consonants voice analysis |
| url | https://ieeexplore.ieee.org/document/9650872/ |
| work_keys_str_mv | AT federicaamato speechimpairmentinparkinsonx2019sdiseaseacousticanalysisofunvoicedconsonantsinitaliannativespeakers AT luigiborzi speechimpairmentinparkinsonx2019sdiseaseacousticanalysisofunvoicedconsonantsinitaliannativespeakers AT gabriellaolmo speechimpairmentinparkinsonx2019sdiseaseacousticanalysisofunvoicedconsonantsinitaliannativespeakers AT carloalbertoartusi speechimpairmentinparkinsonx2019sdiseaseacousticanalysisofunvoicedconsonantsinitaliannativespeakers AT gabrieleimbalzano speechimpairmentinparkinsonx2019sdiseaseacousticanalysisofunvoicedconsonantsinitaliannativespeakers AT leonardolopiano speechimpairmentinparkinsonx2019sdiseaseacousticanalysisofunvoicedconsonantsinitaliannativespeakers |