Parkinson's disease (PD) and essential tremor (ET) are prevalent movement disorders that mainly affect elderly people, presenting diagnostic challenges due to shared clinical features. While both disorders exhibit distinct speech patterns-hypokinetic dysarthria in PD and hyperkinetic dysarthria in ET-the efficacy of speech assessment for differentiation remains unexplored. Developing technology for automatic discrimination could enable early diagnosis and continuous monitoring. However, the lack of data for investigating speech behavior in these patients has inhibited the development of a framework for diagnostic support. In addition, phonetic variability across languages poses practical challenges in establishing a universal speech assessment system. Therefore, it is necessary to develop models robust to the phonetic variability present in different languages worldwide. We propose a method based on Gaussian mixture models to assess domain adaptation from models trained in German and Spanish to classify PD and ET patients in Czech. We modeled three different speech dimensions: articulation, phonation, and prosody and evaluated the models' performance in both bi-class and tri-class classification scenarios (with the addition of healthy controls). Our results show that a fusion of the three speech dimensions achieved optimal results in binary classification, with accuracies up to 81.4 and 86.2% for monologue and /pa-ta-ka/ tasks, respectively. In tri-class scenarios, incorporating healthy speech signals resulted in accuracies of 63.3 and 71.6% for monologue and /pa-ta-ka/ tasks, respectively. Our findings suggest that automated speech analysis, combined with machine learning is robust, accurate, and can be adapted to different languages to distinguish between PD and ET patients.

Department of Circuit Theory Czech Technical University Prague Prague Czech Republic

GITA Lab Faculty of Engineering University of Antioquia Medellín Colombia

Pattern Recognition Lab Friedrich Alexander Universität Erlangen Nürnberg Erlangen Germany

Zobrazit více v PubMed

Haubenberger D, Hallett M. Essential tremor. N. Eng. J. Med. 2018;378:1802–1810. doi: 10.1056/NEJMcp1707928. PubMed DOI

Bloem BR, Okun MS, Klein C. Parkinson’s disease. Lancet. 2021;397:2284–2303. doi: 10.1016/S0140-6736(21)00218-X. PubMed DOI

Thenganatt MA, Louis ED. Distinguishing essential tremor from Parkinson’s disease: bedside tests and laboratory evaluations. Expert Rev. Neurother. 2012;12:687–696. doi: 10.1586/ern.12.49. PubMed DOI PMC

Portalete, C. R. et al. Acoustic and physiological voice assessment and maximum phonation time in patients with different types of dysarthria. J. Voice10.1016/j.jvoice.2021.09.034 (2021). PubMed

Jain S, Lo SE, Louis ED. Common misdiagnosis of a common neurological disorder: how are we misdiagnosing essential tremor? Arch. Neurol. 2006;63:1100–1104. doi: 10.1001/archneur.63.8.1100. PubMed DOI

Schrag A, et al. Essential tremor: an overdiagnosed condition? J. Neurol. 2000;247:955–959. doi: 10.1007/s004150070053. PubMed DOI

Rusz J, Tykalova T, Ramig LO, Tripoliti E. Guidelines for speech recording and acoustic analyses in dysarthrias of movement disorders. Mov. Disord. 2021;36:803–814. doi: 10.1002/mds.28465. PubMed DOI

Pinto S, et al. Treatments for dysarthria in Parkinson’s disease. Lancet Neurol. 2004;3:547–556. doi: 10.1016/S1474-4422(04)00854-3. PubMed DOI

Duffy, J. R. Motor Speech Disorders: Substrates, Differential Diagnosis, and Management 4th ed. (Mosby, 2019).

Sternberg EJ, Alcalay RN, Levy OA, Louis ED. Postural and intention tremors: a detailed clinical study of essential tremor vs. Parkinson’s disease. Front. Neurol. 2013;4:51. doi: 10.3389/fneur.2013.00051. PubMed DOI PMC

Loaiza Duque JD, et al. TremorSoft: an decision support application for differential diagnosis between Parkinson’s disease and essential tremor. SoftwareX. 2023;22:101393. doi: 10.1016/j.softx.2023.101393. DOI

Lin S, et al. Wearable sensor-based gait analysis to discriminate early Parkinson’s disease from essential tremor. J. Neurol. 2023;270:1–19. doi: 10.1007/s00415-023-11577-6. PubMed DOI PMC

Breit S, Spieker S, Schulz JB, Gasser T. Long-term EMG recordings differentiate between parkinsonian and essential tremor. J. Neurol. 2008;255:103–111. doi: 10.1007/s00415-008-0712-2. PubMed DOI

Lin P-C, Chen K-H, Yang B-S, Chen Y-J. A digital assessment system for evaluating kinetic tremor in essential tremor and Parkinson’s disease. BMC Neurol. 2018;18:1–8. doi: 10.1186/s12883-018-1027-2. PubMed DOI PMC

Wang J, et al. Neuromelanin-sensitive MRI of the substantia nigra: an imaging biomarker to differentiate essential tremor from tremor-dominant Parkinson’s disease. Parkinsonism Relat. Disord. 2019;58:3–8. doi: 10.1016/j.parkreldis.2018.07.007. PubMed DOI

Nishio M, Niimi S. Speaking rate and its components in dysarthric speakers. Clin. Linguist. Phon. 2001;15:309–317. doi: 10.1080/02699200010024456. DOI

Rusz J, Hlavnička J, Čmejla R, Ružička E. Automatic evaluation of speech rhythm instability and acceleration in dysarthrias associated with basal ganglia dysfunction. Front. Bioeng. Biotechnol. 2015;3:104. doi: 10.3389/fbioe.2015.00104. PubMed DOI PMC

Favaro A, et al. Multilingual evaluation of interpretable biomarkers to represent language and speech patterns in Parkinson’s disease. Front. Neurol. 2023;14:317. doi: 10.3389/fneur.2023.1142642. PubMed DOI PMC

Vásquez-Correa, J. C. et al. Convolutional neural networks and a transfer learning strategy to classify Parkinson’s disease from speech in three different languages. In Proc. CIARP (2019).

Pinto S, et al. A cross-linguistic perspective to the study of dysarthria in Parkinson’s disease. J. Phon. 2017;64:156–167. doi: 10.1016/j.wocn.2017.01.009. DOI

Rusz J, et al. Speech biomarkers in rapid eye movement sleep behavior disorder and Parkinson disease. Ann. Neurol. 2021;90:62–75. doi: 10.1002/ana.26085. PubMed DOI PMC

Orozco-Arroyave, J. R. Analysis of Speech of People with Parkinson’s Disease Vol. 41 (Logos-Verlag, 2016).

Rusz J, et al. Defining speech subtypes in de novo Parkinson disease: response to long-term levodopa therapy. Neurology. 2021;97:e2124–e2135. doi: 10.1212/WNL.0000000000012878. PubMed DOI

Dehqan A, et al. The effects of aging on acoustic parameters of voice. Folia Phoniatr. Logop. 2013;64:265–270. doi: 10.1159/000343998. PubMed DOI

Louis ED, Faust PL. Essential tremor: the most common form of cerebellar degeneration? Cerebellum Ataxias. 2020;7:1–10. doi: 10.1186/s40673-020-00121-1. PubMed DOI PMC

Rozenstoks K, Novotny M, Horakova D, Rusz J. Automated assessment of oral diadochokinesis in multiple sclerosis using a neural network approach: effect of different syllable repetition paradigms. IEEE Trans. Neural Syst. Rehabil. Eng. 2019;28:32–41. doi: 10.1109/TNSRE.2019.2943064. PubMed DOI

Heeringa W, Gooskens C, van Heuven VJ. Comparing germanic, romance and slavic: Relationships among linguistic distances. Lingua. 2023;287:103512. doi: 10.1016/j.lingua.2023.103512. DOI

Avila, A. R. et al. Improving the performance of far-field speaker verification using multi-condition training: the case of GMM-UBM and i-vector systems. In Proc. ISCA 1096–1100 (International Speech Communication Association, 2014).

Orozco-Arroyave, J. R. et al. New spanish speech corpus database for the analysis of people suffering from Parkinson’s disease. In Proc. LREC (Evaluations and Language resources Distribution Agency, 2014).

Skodda S, Visser W, Schlegel U. Vowel articulation in Parkinson’s disease. J. Voice. 2011;25:467–472. doi: 10.1016/j.jvoice.2010.01.009. PubMed DOI

Rusz J, Tykalová T. Does cognitive impairment influence motor speech performance in de novo Parkinson’s disease? Mov. Disord. 2021;36:2980–2982. doi: 10.1002/mds.28836. PubMed DOI

Simpson AP. Phonetic differences between male and female speech. Lang. Linguist. Compass. 2009;3:621–640. doi: 10.1111/j.1749-818X.2009.00125.x. DOI

Louis ED, et al. Neuropathological changes in essential tremor: 33 cases compared with 21 controls. Brain. 2007;130:3297–3307. doi: 10.1093/brain/awm266. PubMed DOI

Postuma RB, et al. MDS clinical diagnostic criteria for Parkinson’s disease. Mov. Disord. 2015;30:1591–1601. doi: 10.1002/mds.26424. PubMed DOI

Stebbins GT, Goetz C. Factor structure of the unified Parkinson’s disease rating scale: motor examination section. Mov. Disorder. 1998;13:633–636. doi: 10.1002/mds.870130404. PubMed DOI

Elble R, et al. Reliability of a new scale for essential tremor. Mov. Disord. 2012;27:1567–1569. doi: 10.1002/mds.25162. PubMed DOI PMC

Vásquez-Correa JC, et al. Parallel representation learning for the classification of pathological speech: studies on Parkinson’s disease and cleft lip and palate. Speech Commun. 2020;122:56–67. doi: 10.1016/j.specom.2020.07.005. DOI

Arias-Vergara T, et al. Multi-channel spectrograms for speech processing applications using deep learning methods. Pattern Anal. Appl. 2021;24:423–431. doi: 10.1007/s10044-020-00921-5. DOI

Goetz CG, et al. Movement disorder society-sponsored revision of the Unified Parkinson’s Disease Rating Scale (MDS-UPDRS): scale presentation and clinimetric testing results. Mov. Disord. 2008;23:2129–2170. doi: 10.1002/mds.22340. PubMed DOI

Mena, C. D. & Camacho, A. Ciempiess: a new open-sourced mexican spanish radio corpus. In Proc. LREC (2014).

Wahlster, W. Verbmobil: Foundations of Speech-to-Speech Translation (Springer Science & Business Media, 2013).

Orozco-Arroyave JR, et al. Neurospeech: an open-source software for Parkinson’s speech analysis. Digit. Signal Process. 2018;77:207–221. doi: 10.1016/j.dsp.2017.07.004. DOI

Orozco-Arroyave, J. R. et al. Voiced/unvoiced transitions in speech as a potential bio-marker to detect Parkinson’s disease. In Proc. INTERSPEECH, 95-99 (International Speech Communication Association, 2015).

Vásquez-Correa, J. C., Orozco-Arroyave, J. R. & Nöth, E. Convolutional neural network to model articulation impairments in patients with Parkinson’s disease. In Proc. INTERSPEECH, 95-99 (International Speech Communication Association, 2017).

Boersma P. Praat, a system for doing phonetics by computer. Glot. Int. 2001;5:341–345.

Orozco-Arroyave J, et al. Neurospeech: an open-source software for Parkinson’s speech analysis. Digit. Signal Process. 2018;77:207–221. doi: 10.1016/j.dsp.2017.07.004. DOI

Vásquez-Correa JC, Orozco-Arroyave JR, Bocklet T, Nöth E. Towards an automatic evaluation of the dysarthria level of patients with Parkinson’s disease. J. Commun. Disord. 2018;76:21–36. doi: 10.1016/j.jcomdis.2018.08.002. PubMed DOI

Arias-Vergara T, Vásquez-Correa JC, Orozco-Arroyave JR. Parkinson’s disease and aging: analysis of their effect in phonation and articulation of speech. Cognit. Comput. 2017;9:731–748. doi: 10.1007/s12559-017-9497-x. DOI

Dehak N, Dumouchel P, Kenny P. Modeling prosodic features with joint factor analysis for speaker verification. IEEE Trans. Audio Speech Lang. Process. 2007;15:2095–2103. doi: 10.1109/TASL.2007.902758. DOI

Dempster AP, Laird NM, Rubin DB. Maximum likelihood from incomplete data via the EM algorithm. J. R. Stat. Soc. Ser. B Methodol. 1977;39:1–22.

Reynolds DA, Quatieri TF, Dunn RB. Speaker verification using adapted Gaussian mixture models. Digit. Signal Process. 2000;10:19–41. doi: 10.1006/dspr.1999.0361. DOI

Gauvain J-L, Lee C-H. Maximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chains. IEEE Trans. Speech Audio Process. 1994;2:291–298. doi: 10.1109/89.279278. DOI