Spoken Language Alterations can Predict Phenoconversion in Isolated Rapid Eye Movement Sleep Behavior Disorder: A Multicenter Study.

OBJECTIVE: This study assessed the relationship between speech and language impairment and outcome in a multicenter cohort of isolated/idiopathic rapid eye movement (REM) sleep behavior disorder (iRBD). METHODS: Patients with iRBD from 7 centers speaking Czech, English, German, French, and Italian languages underwent a detailed speech assessment at baseline. Story-tale narratives were transcribed and linguistically annotated using fully automated methods based on automatic speech recognition and natural language processing algorithms, leading to the 3 distinctive linguistic and 2 acoustic patterns of language deterioration and associated composite indexes of their overall severity. Patients were then prospectively followed and received assessments for parkinsonism or dementia during follow-up. The Cox proportional hazard was performed to evaluate the predictive value of language patterns for phenoconversion over a follow-up period of 5 years. RESULTS: Of 180 patients free of parkinsonism or dementia, 156 provided follow-up information. After a mean follow-up of 2.7 years, 42 (26.9%) patients developed neurodegenerative disease. Patients with higher severity of linguistic abnormalities (hazard ratio [HR = 2.35]) and acoustic abnormalities (HR = 1.92) were more likely to develop a defined neurodegenerative disease, with converters having lower content richness (HR = 1.74), slower articulation rate (HR = 1.58), and prolonged pauses (HR = 1.46). Dementia-first (n = 16) and parkinsonism-first with mild cognitive impairment (n = 9) converters had higher severity of linguistic abnormalities than parkinsonism-first with normal cognition converters (n = 17). INTERPRETATION: Automated language analysis might provide a predictor of phenoconversion from iRBD into synucleinopathy subtypes with cognitive impairment, and thus can be used to stratify patients for neuroprotective trials. ANN NEUROL 2024;95:530-543.

Speech Biomarkers in Rapid Eye Movement Sleep Behavior Disorder and Parkinson Disease.

OBJECTIVE: This multilanguage study used simple speech recording and high-end pattern analysis to provide sensitive and reliable noninvasive biomarkers of prodromal versus manifest α-synucleinopathy in patients with idiopathic rapid eye movement sleep behavior disorder (iRBD) and early-stage Parkinson disease (PD). METHODS: We performed a multicenter study across the Czech, English, German, French, and Italian languages at 7 centers in Europe and North America. A total of 448 participants (337 males), including 150 with iRBD (mean duration of iRBD across language groups 0.5-3.4 years), 149 with PD (mean duration of disease across language groups 1.7-2.5 years), and 149 healthy controls were recorded; 350 of the participants completed the 12-month follow-up. We developed a fully automated acoustic quantitative assessment approach for the 7 distinctive patterns of hypokinetic dysarthria. RESULTS: No differences in language that impacted clinical parkinsonian phenotypes were found. Compared with the controls, we found significant abnormalities of an overall acoustic speech severity measure via composite dysarthria index for both iRBD (p = 0.002) and PD (p < 0.001). However, only PD (p < 0.001) was perceptually distinct in a blinded subjective analysis. We found significant group differences between PD and controls for monopitch (p < 0.001), prolonged pauses (p < 0.001), and imprecise consonants (p = 0.03); only monopitch was able to differentiate iRBD patients from controls (p = 0.004). At the 12-month follow-up, a slight progression of overall acoustic speech impairment was noted for the iRBD (p = 0.04) and PD (p = 0.03) groups. INTERPRETATION: Automated speech analysis might provide a useful additional biomarker of parkinsonism for the assessment of disease progression and therapeutic interventions. ANN NEUROL 2021;90:62-75.

Acoustic assessment in mandarin-speaking Parkinson's disease patients and disease progression monitoring and brain impairment within the speech subsystem.

Approximately 90% of Parkinson's patients (PD) suffer from dysarthria. However, there is currently a lack of research on acoustic measurements and speech impairment patterns among Mandarin-speaking individuals with PD. This study aims to assess the diagnosis and disease monitoring possibility in Mandarin-speaking PD patients through the recommended speech paradigm for non-tonal languages, and to explore the anatomical and functional substrates. We examined total of 160 native Mandarin-speaking Chinese participants consisting of 80 PD patients, 40 healthy controls (HC), and 40 MRI controls. We screened the optimal acoustic metric combination for PD diagnosis. Finally, we used the objective metrics to predict the patient's motor status using the Naïve Bayes model and analyzed the correlations between cortical thickness, subcortical volumes, functional connectivity, and network properties. Comprehensive acoustic screening based on prosodic, articulation, and phonation abnormalities allows differentiation between HC and PD with an area under the curve of 0.931. Patients with slowed reading exhibited atrophy of the fusiform gyrus (FDR p = 0.010, R = 0.391), reduced functional connectivity between the fusiform gyrus and motor cortex, and increased nodal local efficiency (NLE) and nodal efficiency (NE) in bilateral pallidum. Patients with prolonged pauses demonstrated atrophy in the left hippocampus, along with decreased NLE and NE. The acoustic assessment in Mandarin proves effective in diagnosis and disease monitoring for Mandarin-speaking PD patients, generalizing standardized acoustic guidelines beyond non-tonal languages. The speech impairment in Mandarin-speaking PD patients not only involves motor aspects of speech but also encompasses the cognitive processes underlying language generation.

The automated screening of speech motor development in children based on the sequential motion rate.

BACKGROUND: Motor skills in children have traditionally been examined via challenging speech tasks such as syllable repetition, and calculating the syllabic rate using a stopwatch or by inspecting the oscillogram followed by a laborious comparison of the scores on a look-up table representing the typical performances of children of the given age and sex. As the commonly used performance tables are over-simplified to allow for manual scoring, we raise the question of whether a computational model of motor skills development could be more informative, and could allow for the automated screening of children to detect underdeveloped motor skills. METHODS: We recruited a total of 275 children aged four to 15 years. All the participants were native Czech speakers with no history of hearing or neurological impairments. We recorded each child's performance of/pa/-/ta/-/ka/syllable repetition. Various parameters of diadochokinesis (DDK; DDK rate, DDK regularity, voice onset time [VOT] ratio, syllable, vowel and VOT duration) were investigated in the acoustic signals using supervised reference labels. Female and male participants were analyzed separately by comparing younger, middle, and older age groups of children via ANOVA. Finally, we implemented a fully automated model that estimated the developmental age of a child based on the acoustic signal, and evaluated its accuracy using Pearson's correlation coefficient and normalized root-mean-squared errors (RMSEs). RESULTS: The DDK rate reflected the ages of the children proportionally (p < 0.001). Other DDK parameters also showed strong sensitivity to age (p < 0.001), with the exception of VOT duration, which had a smaller effect (p = 0.091). The effect of age was found to be sex specific for the syllable length (p < 0.001) and DDK rate (p = 0.003). We observed that females spoke more slowly and had a longer VOT at preschool age (p < 0.001). The DDK rate obtained via the automated algorithm was strongly correlated with the reference (p < 0.001, Pearson's correlation coefficient of 0.97), with a low normalized RMSE of 3.77%. CONCLUSIONS: As children develop their motor skills, they are capable of shortening the vowels to increase the rate of syllabic repetitions. The nonlinear development in childhood and adolescence, with a steady state in adulthood, follows a logistic function for the DDK rate. This study demonstrates that the development of motor skills can be examined sensitively and more appropriately by a fully automated noninvasive procedure that also accounts for the dispersion of values within age brackets.

Characterizing vocal tremor in progressive neurological diseases via automated acoustic analyses.

OBJECTIVE: Voice tremor represents a common but frequently overlooked clinical feature of neurological disease. Therefore, we aimed to quantitatively and objectively assess the characteristics of voice tremor in a large sample of patients with various progressive neurological diseases. METHODS: Voice samples were acquired from 240 patients with neurological disease and 40 healthy controls. The robust automated method was designed, allowing precise tracking of multiple tremor frequencies and distinguish pathological from the physiological tremor. RESULTS: Abnormal tremor was revealed in Huntington's disease (65%), essential tremor (50%), multiple system atrophy (40%), cerebellar ataxia (40%), amyotrophic lateral sclerosis (40%), progressive supranuclear palsy (25%), Parkinson's disease (20%), cervical dystonia (10%), and multiple sclerosis (8%) but not in controls. Low-frequency voice tremor (<4 Hz) was common in all investigated diseases, whereas medium tremor frequencies (4-7 Hz) were specific for movement disorders of Parkinson's disease, multiple system atrophy, essential tremor, and cervical dystonia. CONCLUSIONS: Careful estimation of vocal tremor may help with accurate diagnosis and tailored treatment. SIGNIFICANCE: This study provides (i) more insights into the pathophysiology of vocal tremor in a wide range of neurological diseases and (ii) an accurate method for estimation of vocal tremor suitable for clinical practice.

Smartphone Allows Capture of Speech Abnormalities Associated With High Risk of Developing Parkinson's Disease.

Although smartphone technology provides new opportunities for the recording of speech samples in everyday life, its ability to capture prodromal speech impairment in persons with a high risk of developing Parkinson's disease (PD) has never been investigated. Speech data were acquired through a smartphone as well as a professional microphone with a linear frequency response from 50 participants with a rapid eye movement sleep behavior disorder that are at a high risk of developing PD and related neurodegenerative disorders. Additionally, recordings of 30 newly diagnosed, untreated PD patients and 30 healthy participants were evaluated. Acoustic assessment of 11 speech dimensions representing the key aspects of hypokinetic dysarthria in the early stages of PD was performed. Smartphone allowed the detection of speech abnormalities in participants with a high risk of developing PD. Acoustic measurements related to fundamental frequency variability, duration of pause intervals, and rate of speech timing extracted from spontaneous speech were sufficiently sensitive to significantly separate groups (area under curve of 0.85 between PD and controls) and showed very strong correlation and reliability between the professional microphone and the smartphone. Speech-based biomarkers collected through smartphones may have the potential to revolutionize the diagnostic process in neurodegenerative diseases and improve stratification for future neuroprotective therapy in PD.

Characteristics of motor speech phenotypes in multiple sclerosis.

BACKGROUND: Motor speech disorders in multiple sclerosis (MS) are poorly understood and their quantitative, objective acoustic characterization remains limited. Additionally, little data regarding relationships between the severity of speech disorders and neurological involvement in MS, as well as the contribution of pyramidal and cerebellar functional systems on speech phenotypes, is available. METHODS: Speech data were acquired from 141 MS patients with Expanded Disability Status Scale (EDSS) ranging from 1 to 6.5 and 70 matched healthy controls. Objective acoustic speech assessment including subtests on phonation, oral diadochokinesis, articulation and prosody was performed. RESULTS: The prevalence of dysarthria in our MS cohort was 56% while the severity was generally mild and primarily consisted of a combination of spastic and ataxic components. Prosodic-articulatory disorder presenting with monopitch, articulatory decay, excess loudness variations and slow rate was the most salient. Speech disorders reflected subclinical motor impairment with 78% accuracy in discriminating between a subgroup of asymptomatic MS (EDSS < 2.0) and control speakers. Speech disorder severity was related to the severity of neurological involvement. Decreased articulation rate was moderately correlated to EDSS as well as all subtests of the multiple sclerosis functional composite. The strongest correlation was observed between irregular oral diadochokinesis and the 9-Hole Peg Test (r = - 0.65, p < 0.001). Irregular oral diadochokinesis and excess loudness variations significantly separated pure pyramidal and mixed pyramidal-cerebellar MS subgroups. CONCLUSIONS: Automated speech analyses may provide valuable biomarkers of disease progression in MS as dysarthria represents common and early manifestation that reflects disease disability and underlying pyramidal-cerebellar pathophysiology.

Automated analysis of connected speech reveals early biomarkers of Parkinson's disease in patients with rapid eye movement sleep behaviour disorder.

For generations, the evaluation of speech abnormalities in neurodegenerative disorders such as Parkinson's disease (PD) has been limited to perceptual tests or user-controlled laboratory analysis based upon rather small samples of human vocalizations. Our study introduces a fully automated method that yields significant features related to respiratory deficits, dysphonia, imprecise articulation and dysrhythmia from acoustic microphone data of natural connected speech for predicting early and distinctive patterns of neurodegeneration. We compared speech recordings of 50 subjects with rapid eye movement sleep behaviour disorder (RBD), 30 newly diagnosed, untreated PD patients and 50 healthy controls, and showed that subliminal parkinsonian speech deficits can be reliably captured even in RBD patients, which are at high risk of developing PD or other synucleinopathies. Thus, automated vocal analysis should soon be able to contribute to screening and diagnostic procedures for prodromal parkinsonian neurodegeneration in natural environments.

High-accuracy voice-based classification between patients with Parkinson's disease and other neurological diseases may be an easy task with inappropriate experimental design.

Recently, based on voice cepstral analysis, Benba et al. (IEEE T. Neur. Sys. Reh., vol. 24, pp. 1100-1108, 2016) have reported discrimination between patients with Parkinson's disease and different neurological disorders with high classification accuracy up to 90%. Using the same approach, we were able to experimentally separate two groups of normal healthy speakers with 96% classification accuracy and showed that the method proposed by Benba et al. may not be appropriate for discrimination between different neurological diseases. In particular, voice cepstral analysis appears to be sensitive to specific speakers' characteristics such as gender or age. Our findings emphasize several assumptions that can be considered as basic necessary conditions for research reporting speech data in progressive neurodegenerative diseases.

Quantitative assessment of motor speech abnormalities in idiopathic rapid eye movement sleep behaviour disorder.

OBJECTIVE: Patients with idiopathic rapid eye movement sleep behaviour disorder (RBD) are at substantial risk for developing Parkinson's disease (PD) or related neurodegenerative disorders. Speech is an important indicator of motor function and movement coordination, and therefore may be an extremely sensitive early marker of changes due to prodromal neurodegeneration. METHODS: Speech data were acquired from 16 RBD subjects and 16 age- and sex-matched healthy control subjects. Objective acoustic assessment of 15 speech dimensions representing various phonatory, articulatory, and prosodic deviations was performed. Statistical models were applied to characterise speech disorders in RBD and to estimate sensitivity and specificity in differentiating between RBD and control subjects. RESULTS: Some form of speech impairment was revealed in 88% of RBD subjects. Articulatory deficits were the most prominent findings in RBD. In comparison to controls, the RBD group showed significant alterations in irregular alternating motion rates (p = 0.009) and articulatory decay (p = 0.01). The combination of four distinctive speech dimensions, including aperiodicity, irregular alternating motion rates, articulatory decay, and dysfluency, led to 96% sensitivity and 79% specificity in discriminating between RBD and control subjects. Speech impairment was significantly more pronounced in RBD subjects with the motor score of the Unified Parkinson's Disease Rating Scale greater than 4 points when compared to other RBD individuals. CONCLUSION: Simple quantitative speech motor measures may be suitable for the reliable detection of prodromal neurodegeneration in subjects with RBD, and therefore may provide important outcomes for future therapy trials.

Automatic Evaluation of Speech Rhythm Instability and Acceleration in Dysarthrias Associated with Basal Ganglia Dysfunction.

Speech rhythm abnormalities are commonly present in patients with different neurodegenerative disorders. These alterations are hypothesized to be a consequence of disruption to the basal ganglia circuitry involving dysfunction of motor planning, programing, and execution, which can be detected by a syllable repetition paradigm. Therefore, the aim of the present study was to design a robust signal processing technique that allows the automatic detection of spectrally distinctive nuclei of syllable vocalizations and to determine speech features that represent rhythm instability (RI) and rhythm acceleration (RA). A further aim was to elucidate specific patterns of dysrhythmia across various neurodegenerative disorders that share disruption of basal ganglia function. Speech samples based on repetition of the syllable /pa/ at a self-determined steady pace were acquired from 109 subjects, including 22 with Parkinson's disease (PD), 11 progressive supranuclear palsy (PSP), 9 multiple system atrophy (MSA), 24 ephedrone-induced parkinsonism (EP), 20 Huntington's disease (HD), and 23 healthy controls. Subsequently, an algorithm for the automatic detection of syllables as well as features representing RI and RA were designed. The proposed detection algorithm was able to correctly identify syllables and remove erroneous detections due to excessive inspiration and non-speech sounds with a very high accuracy of 99.6%. Instability of vocal pace performance was observed in PSP, MSA, EP, and HD groups. Significantly increased pace acceleration was observed only in the PD group. Although not significant, a tendency for pace acceleration was observed also in the PSP and MSA groups. Our findings underline the crucial role of the basal ganglia in the execution and maintenance of automatic speech motor sequences. We envisage the current approach to become the first step toward the development of acoustic technologies allowing automated assessment of rhythm in dysarthrias.