Automatic speech-based assessment to discriminate Parkinson's disease from essential tremor with a cross-language approach.

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.

Vision Transformer for Parkinson's Disease Classification using Multilingual Sustained Vowel Recordings.

Parkinson's disease (PD) is the 2nd most prevalent neurodegenerative disease in the world. Thus, the early detection of PD has recently been the subject of several scientific and commercial studies. In this paper, we propose a pipeline using Vision Transformer applied to mel-spectrograms for PD classification using multilingual sustained vowel recordings. Furthermore, our proposed transformed-based model shows a great potential to use voice as a single modality biomarker for automatic PD detection without language restrictions, a wide range of vowels, with an F1-score equal to 0.78. The results of our study fall within the range of the estimated prevalence of voice and speech disorders in Parkinson's disease, which ranges from 70-90%. Our study demonstrates a high potential for adaptation in clinical decision-making, allowing for increasingly systematic and fast diagnosis of PD with the potential for use in telemedicine.Clinical relevance- There is an urgent need to develop non invasive biomarker of Parkinson's disease effective enough to detect the onset of the disease to introduce neuroprotective treatment at the earliest stage possible and to follow the results of that intervention. Voice disorders in PD are very frequent and are expected to be utilized as an early diagnostic biomarker. The voice analysis using deep neural networks open new opportunities to assess neurodegenerative diseases' symptoms, for fast diagnosis-making, to guide treatment initiation, and risk prediction. The detection accuracy for voice biomarkers according to our method reached close to the maximum achievable value.

Deep Learning and Artificial Intelligence Applied to Model Speech and Language in Parkinson's Disease.

Parkinson's disease (PD) is the second most prevalent neurodegenerative disorder in the world, and it is characterized by the production of different motor and non-motor symptoms which negatively affect speech and language production. For decades, the research community has been working on methodologies to automatically model these biomarkers to detect and monitor the disease; however, although speech impairments have been widely explored, language remains underexplored despite being a valuable source of information, especially to assess cognitive impairments associated with non-motor symptoms. This study proposes the automatic assessment of PD patients using different methodologies to model speech and language biomarkers. One-dimensional and two-dimensional convolutional neural networks (CNNs), along with pre-trained models such as Wav2Vec 2.0, BERT, and BETO, were considered to classify PD patients vs. Healthy Control (HC) subjects. The first approach consisted of modeling speech and language independently. Then, the best representations from each modality were combined following early, joint, and late fusion strategies. The results show that the speech modality yielded an accuracy of up to 88%, thus outperforming all language representations, including the multi-modal approach. These results suggest that speech representations better discriminate PD patients and HC subjects than language representations. When analyzing the fusion strategies, we observed that changes in the time span of the multi-modal representation could produce a significant loss of information in the speech modality, which was likely linked to a decrease in accuracy in the multi-modal experiments. Further experiments are necessary to validate this claim with other fusion methods using different time spans.

Pilot Study: Magnetic Motion Analysis for Swallowing Detection Using MEMS Cantilever Actuators.

The swallowing process involves complex muscle coordination mechanisms. When alterations in such mechanisms are produced by neurological conditions or diseases, a swallowing disorder known as dysphagia occurs. The instrumental evaluation of dysphagia is currently performed by invasive and experience-dependent techniques. Otherwise, non-invasive magnetic methods have proven to be suitable for various biomedical applications and might also be applicable for an objective swallowing assessment. In this pilot study, we performed a novel approach for deglutition evaluation based on active magnetic motion sensing with permanent magnet cantilever actuators. During the intake of liquids with different consistency, we recorded magnetic signals of relative movements between a stationary sensor and a body-worn actuator on the cricoid cartilage. Our results indicate the detection capability of swallowing-related movements in terms of a characteristic pattern. Consequently, the proposed technique offers the potential for dysphagia screening and biofeedback-based therapies.

Exploring facial expressions and action unit domains for Parkinson detection.

BACKGROUND AND OBJECTIVE: Patients suffering from Parkinson's disease (PD) present a reduction in facial movements called hypomimia. In this work, we propose to use machine learning facial expression analysis from face images based on action unit domains to improve PD detection. We propose different domain adaptation techniques to exploit the latest advances in automatic face analysis and face action unit detection. METHODS: Three different approaches are explored to model facial expressions of PD patients: (i) face analysis using single frame images and also using sequences of images, (ii) transfer learning from face analysis to action units recognition, and (iii) triplet-loss functions to improve the automatic classification between patients and healthy subjects. RESULTS: Real face images from PD patients show that it is possible to properly model elicited facial expressions using image sequences (neutral, onset-transition, apex, offset-transition, and neutral) with accuracy improvements of up to 5.5% (from 72.9% to 78.4%) with respect to single-image PD detection. We also show that our proposed action unit domain adaptation provides improvements of up to 8.9% (from 78.4% to 87.3%) with respect to face analysis. Finally, we also show that triplet-loss functions provide improvements of up to 3.6% (from 78.8% to 82.4%) with respect to action unit domain adaptation applied upon models created from scratch. The code of the experiments is available at https://github.com/luisf-gomez/Explorer-FE-AU-in-PD. CONCLUSIONS: Domain adaptation via transfer learning methods seem to be a promising strategy to model hypomimia in PD patients. Considering the good results and also the fact that only up to five images per participant are considered in each sequence, we believe that this work is a step forward in the development of inexpensive computational systems suitable to model and quantify problems of PD patients in their facial expressions.

Adult Cochlear Implant Users Versus Typical Hearing Persons: An Automatic Analysis of Acoustic-Prosodic Parameters.

PURPOSE: The aim of this study was to investigate the speech prosody of postlingually deaf cochlear implant (CI) users compared with control speakers without hearing or speech impairment. METHOD: Speech recordings of 74 CI users (37 males and 37 females) and 72 age-balanced control speakers (36 males and 36 females) are considered. All participants are German native speakers and read Der Nordwind und die Sonne (The North Wind and the Sun), a standard text in pathological speech analysis and phonetic transcriptions. Automatic acoustic analysis is performed considering pitch, loudness, and duration features, including speech rate and rhythm. RESULTS: In general, duration and rhythm features differ between CI users and control speakers. CI users read slower and have a lower voiced segment ratio compared with control speakers. A lower voiced ratio goes along with a prolongation of the voiced segments' duration in male and with a prolongation of pauses in female CI users. Rhythm features in CI users have higher variability in the duration of vowels and consonants than in control speakers. The use of bilateral CIs showed no advantages concerning speech prosody features in comparison to unilateral use of CI. CONCLUSIONS: Even after cochlear implantation and rehabilitation, the speech of postlingually deaf adults deviates from the speech of control speakers, which might be due to changed auditory feedback. We suggest considering changes in temporal aspects of speech in future rehabilitation strategies. SUPPLEMENTAL MATERIAL: https://doi.org/10.23641/asha.21579171.

Detecting Parkinson's disease and its cognitive phenotypes via automated semantic analyses of action stories.

Action-concept outcomes are useful targets to identify Parkinson's disease (PD) patients and differentiate between those with and without mild cognitive impairment (PD-MCI, PD-nMCI). Yet, most approaches employ burdensome examiner-dependent tasks, limiting their utility. We introduce a framework capturing action-concept markers automatically in natural speech. Patients from both subgroups and controls retold an action-laden and a non-action-laden text (AT, nAT). In each retelling, we weighed action and non-action concepts through our automated Proximity-to-Reference-Semantic-Field (P-RSF) metric, for analysis via ANCOVAs (controlling for cognitive dysfunction) and support vector machines. Patients were differentiated from controls based on AT (but not nAT) P-RSF scores. The same occurred in PD-nMCI patients. Conversely, PD-MCI patients exhibited reduced P-RSF scores for both texts. Direct discrimination between patient subgroups was not systematic, but it yielded best outcomes via AT scores. Our approach outperformed classifiers based on corpus-derived embeddings. This framework opens scalable avenues to support PD diagnosis and phenotyping.

Construcción de mapas articulatorios para la detección automática de la enfermedad de Parkinson por medio de la voz / Building articulatory maps for the automatic detection of Parkinson's disease from speech

Antecedentes y objetivo: Las investigaciones recientes han mostrado que el análisis de las señales de habla provee información relevante para el apoyo diagnóstico y monitoreo de pacientes con enfermedad de Parkinson (EP). En este trabajo se propone una metodología para la construcción de mapas articulatorios basados en información articulatoria y fonológica del habla tal que permita la clasificación automática de personas con EP vs. personas asintomáticas y que además logre una fácil visualización e interpretación de los resultados. Materiales y métodos: Se consideraron 100 grabaciones de audio de un texto leído que contiene todos los sonidos del español hablado en Colombia. Se extrajeron características articulatorias y además fonológicas a través de dos herramientas: PhonVoc y Phonet. Luego, a partir del alineamiento forzado se obtuvieron los tiempos de ocurrencia de los fonemas para agrupar las clases fonológicas. Posteriormente se implementaron dos clasificadores, máquinas de soporte vectorial y árboles aleatorios. Resultados: Los experimentos muestran un acierto de hasta 90% en la clasificación de pacientes vs. asintomáticos con la clase fonológica «Vocales» y aciertos superiores al 80% para las clases «Nasales», «Fricativas sordas» y «Oclusivas sonoras». Para facilitar la interpretación visual de los resultados se construyeron mapas articulatorios usando mezclas de modelos Gaussianos (GMMs, por las siglas en inglés de Gaussian Mixture Models) que agruparon las clases fonológicas en dos dimensiones. Conclusiones: La metodología propuesta es una alternativa adecuada tanto para la detección automática de la EP como para la evaluación del déficit articulatorio en los fonemas contenidos en las clases fonológicas.(AU)

Background and objectives: Recent studies have shown that speech analysis provides relevant information to support the diagnosis and monitoring of patients suffering from Parkinson's disease (PD). In this work a methodology is proposed to create articulatory maps based on articulatory and phonological information such that allow a clear and interpretable visualization of the results. Materials and methods: A total of 100 speakers were recorded while reading a text with 36 words that includes all phonemes of the Colombian Spanish. Phonological features are extracted with two toolkits: PhonVoc and Phonet. Forced alignment is used to obtained the time-stamps per phoneme. Support vector machines and random forests are used to classify between PD patients and non-symptomatic subjects. Results: Accuracies of up to 90% are observed when the phonological class «Vowels» is considered and also accuracies above 80% are found for «Nasals», «Voiceless ficatives» and «Voiced Stop». Articulatory maps are created based on Gaussian mixture models with the aim to enable the interpretation of results. Conclusions: The proposed methodology is suitable for the automatic detection of PD and also to assess possible articulatory deficits in the production of specific phonological classes.(AU)

Comparison of CNN-Learned vs. Handcrafted Features for Detection of Parkinson's Disease Dysgraphia in a Multilingual Dataset.

Parkinson's disease dysgraphia (PDYS), one of the earliest signs of Parkinson's disease (PD), has been researched as a promising biomarker of PD and as the target of a noninvasive and inexpensive approach to monitoring the progress of the disease. However, although several approaches to supportive PDYS diagnosis have been proposed (mainly based on handcrafted features (HF) extracted from online handwriting or the utilization of deep neural networks), it remains unclear which approach provides the highest discrimination power and how these approaches can be transferred between different datasets and languages. This study aims to compare classification performance based on two types of features: features automatically extracted by a pretrained convolutional neural network (CNN) and HF designed by human experts. Both approaches are evaluated on a multilingual dataset collected from 143 PD patients and 151 healthy controls in the Czech Republic, United States, Colombia, and Hungary. The subjects performed the spiral drawing task (SDT; a language-independent task) and the sentence writing task (SWT; a language-dependent task). Models based on logistic regression and gradient boosting were trained in several scenarios, specifically single language (SL), leave one language out (LOLO), and all languages combined (ALC). We found that the HF slightly outperformed the CNN-extracted features in all considered evaluation scenarios for the SWT. In detail, the following balanced accuracy (BACC) scores were achieved: SL-0.65 (HF), 0.58 (CNN); LOLO-0.65 (HF), 0.57 (CNN); and ALC-0.69 (HF), 0.66 (CNN). However, in the case of the SDT, features extracted by a CNN provided competitive results: SL-0.66 (HF), 0.62 (CNN); LOLO-0.56 (HF), 0.54 (CNN); and ALC-0.60 (HF), 0.60 (CNN). In summary, regarding the SWT, the HF outperformed the CNN-extracted features over 6% (mean BACC of 0.66 for HF, and 0.60 for CNN). In the case of the SDT, both feature sets provided almost identical classification performance (mean BACC of 0.60 for HF, and 0.58 for CNN).

An algorithm for Parkinson's disease speech classification based on isolated words analysis.

INTRODUCTION: Automatic assessment of speech impairment is a cutting edge topic in Parkinson's disease (PD). Language disorders are known to occur several years earlier than typical motor symptoms, thus speech analysis may contribute to the early diagnosis of the disease. Moreover, the remote monitoring of dysphonia could allow achieving an effective follow-up of PD clinical condition, possibly performed in the home environment. METHODS: In this work, we performed a multi-level analysis, progressively combining features extracted from the entire signal, the voiced segments, and the on-set/off-set regions, leading to a total number of 126 features. Furthermore, we compared the performance of early and late feature fusion schemes, aiming to identify the best model configuration and taking advantage of having 25 isolated words pronounced by each subject. We employed data from the PC-GITA database (50 healthy controls and 50 PD patients) for validation and testing. RESULTS: We implemented an optimized k-Nearest Neighbours model for the binary classification of PD patients versus healthy controls. We achieved an accuracy of 99.4% in 10-fold cross-validation and 94.3% in testing on the PC-GITA database (average value of male and female subjects). CONCLUSION: The promising performance yielded by our model confirms the feasibility of automatic assessment of PD using voice recordings. Moreover, a post-hoc analysis of the most relevant features discloses the option of voice processing using a simple smartphone application.

Machine learning based analysis of speech dimensions in functional oropharyngeal dysphagia.

BACKGROUND AND OBJECTIVE: The normal swallowing process requires a complex coordination of anatomical structures driven by sensory and cranial nerves. Alterations in such coordination cause swallowing malfunctions, namely dysphagia. The dysphagia screening methods are quite subjective and experience dependent. Bearing in mind that the swallowing process and speech production share some anatomical structures and mechanisms of neurological control, this work aims to evaluate the suitability of automatic speech processing and machine learning techniques for screening of functional dysphagia. METHODS: Speech recordings were collected from 46 patients with functional oropharyngeal dysphagia produced by neurological causes, and 46 healthy controls. The dimensions of speech including phonation, articulation, and prosody were considered through different speech tasks. Specific features per dimension were extracted and analyzed using statistical tests. Machine learning models were applied per dimension via nested cross-validation. Hyperparameters were selected using the AUC - ROC as optimization criterion. RESULTS: The Random Forest in the articulation related speech tasks retrieved the highest performance measures (AUC=0.86±0.10, sensitivity=0.91±0.12) for individual analysis of dimensions. In addition, the combination of speech dimensions with a voting ensemble improved the results, which suggests a contribution of information from different feature sets extracted from speech signals in dysphagia conditions. CONCLUSIONS: The proposed approach based on speech related models is suitable for the automatic discrimination between dysphagic and healthy individuals. These findings seem to have potential use in the screening of functional oropharyngeal dysphagia in a non-invasive and inexpensive way.

A machine learning perspective on the emotional content of Parkinsonian speech.

Patients with Parkinson's disease (PD) have distinctive voice patterns, often perceived as expressing sad emotion. While this characteristic of Parkinsonian speech has been supported through the perspective of listeners, where both PD and healthy control (HC) subjects repeat the same speaking tasks, it has never been explored through a machine learning modelling approach. Our work provides an objective evaluation of this characteristic of the PD speech, by building a transfer learning system to assess how the PD pathology affects the sadness perception. To do so we introduce a Mixture-of-Experts (MoE) architecture for speech emotion recognition designed to be transferable across datasets. Firstly, by relying on publicly available emotional speech corpora, we train the MoE model and then we use it to quantify perceived sadness in never seen before PD and matched HC speech recordings. To build our models (experts), we extracted spectral features of the voicing parts of speech and we trained a gradient boosting decision trees model in each corpus to predict happiness vs. sadness. MoE predictions are created by weighting each expert's prediction according to the distance between the new sample and the expert-specific training samples. The MoE approach systematically infers more negative emotional characteristics in PD speech than in HC. Crucially, these judgments are related to the disease severity and the severity of speech impairment in the PD patients: the more impairment, the more likely the speech is to be judged as sad. Our findings pave the way towards a better understanding of the characteristics of PD speech and show how publicly available datasets can be used to train models that provide interesting insights on clinical data.

From discourse to pathology: Automatic identification of Parkinson's disease patients via morphological measures across three languages.

Embodied cognition research on Parkinson's disease (PD) points to disruptions of frontostriatal language functions as sensitive targets for clinical assessment. However, no existing approach has been tested for crosslinguistic validity, let alone by combining naturalistic tasks with machine-learning tools. To address these issues, we conducted the first classifier-based examination of morphological processing (a core frontostriatal function) in spontaneous monologues from PD patients across three typologically different languages. The study comprised 330 participants, encompassing speakers of Spanish (61 patients, 57 matched controls), German (88 patients, 88 matched controls), and Czech (20 patients, 16 matched controls). All subjects described the activities they perform during a regular day, and their monologues were automatically coded via morphological tagging, a computerized method that labels each word with a part-of-speech tag (e.g., noun, verb) and specific morphological tags (e.g., person, gender, number, tense). The ensuing data were subjected to machine-learning analyses to assess whether differential morphological patterns could classify between patients and controls and reflect the former's degree of motor impairment. Results showed robust classification rates, with over 80% of patients being discriminated from controls in each language separately. Moreover, the most discriminative morphological features were associated with the patients' motor compromise (as indicated by Pearson r correlations between predicted and collected motor impairment scores that ranged from moderate to moderate-to-strong across languages). Taken together, our results suggest that morphological patterning, an embodied frontostriatal domain, may be distinctively affected in PD across languages and even under ecological testing conditions.

Apkinson: the smartphone application for telemonitoring Parkinson's patients through speech, gait and hands movement.

Aim: This paper introduces Apkinson, a mobile application for motor evaluation and monitoring of Parkinson's disease patients. Materials & methods: The App is based on previously reported methods, for instance, the evaluation of articulation and pronunciation in speech, regularity and freezing of gait in walking, and tapping accuracy in hand movement. Results: Preliminary experiments indicate that most of the measurements are suitable to discriminate patients and controls. Significance is evaluated through statistical tests. Conclusion: Although the reported results correspond to preliminary experiments, we think that Apkinson is a very useful App that can help patients, caregivers and clinicians, in performing a more accurate monitoring of the disease progression. Additionally, the mobile App can be a personal health assistant.

Deep Learning Approach to Parkinson's Disease Detection Using Voice Recordings and Convolutional Neural Network Dedicated to Image Classification.

This study presents an approach to Parkinson's disease detection using vowels with sustained phonation and a ResNet architecture dedicated originally to image classification. We calculated spectrum of the audio recordings and used them as an image input to the ResNet architecture pre-trained using the ImageNet and SVD databases. To prevent overfitting the dataset was strongly augmented in the time domain. The Parkinson's dataset (from PC-GITA database) consists of 100 patients (50 were healthy / 50 were diagnosed with Parkinson's disease). Each patient was recorded 3 times. The obtained accuracy on the validation set is above 90% which is comparable to the current state-of-the-art methods. The results are promising because it turned out that features learned on natural images are able to transfer the knowledge to artificial images representing the spectrogram of the voice signal. What is more, we showed that it is possible to perform a successful detection of Parkinson's disease using only frequency-based features. A spectrogram enables visual representation of frequencies spectrum of a signal. It allows to follow the frequencies changes of a signal in time.

How language flows when movements don't: An automated analysis of spontaneous discourse in Parkinson's disease.

To assess the impact of Parkinson's disease (PD) on spontaneous discourse, we conducted computerized analyses of brief monologues produced by 51 patients and 50 controls. We explored differences in semantic fields (via latent semantic analysis), grammatical choices (using part-of-speech tagging), and word-level repetitions (with graph embedding tools). Although overall output was quantitatively similar between groups, patients relied less heavily on action-related concepts and used more subordinate structures. Also, a classification tool operating on grammatical patterns identified monologues as pertaining to patients or controls with 75% accuracy. Finally, while the incidence of dysfluent word repetitions was similar between groups, it allowed inferring the patients' level of motor impairment with 77% accuracy. Our results highlight the relevance of studying naturalistic discourse features to tap the integrity of neural (and, particularly, motor) networks, beyond the possibilities of standard token-level instruments.

Characterization Methods for the Detection of Multiple Voice Disorders: Neurological, Functional, and Laryngeal Diseases.

This paper evaluates the accuracy of different characterization methods for the automatic detection of multiple speech disorders. The speech impairments considered include dysphonia in people with Parkinson's disease (PD), dysphonia diagnosed in patients with different laryngeal pathologies (LP), and hypernasality in children with cleft lip and palate (CLP). Four different methods are applied to analyze the voice signals including noise content measures, spectral-cepstral modeling, nonlinear features, and measurements to quantify the stability of the fundamental frequency. These measures are tested in six databases: three with recordings of PD patients, two with patients with LP, and one with children with CLP. The abnormal vibration of the vocal folds observed in PD patients and in people with LP is modeled using the stability measures with accuracies ranging from 81% to 99% depending on the pathology. The spectral-cepstral features are used in this paper to model the voice spectrum with special emphasis around the first two formants. These measures exhibit accuracies ranging from 95% to 99% in the automatic detection of hypernasal voices, which confirms the presence of changes in the speech spectrum due to hypernasality. Noise measures suitably discriminate between dysphonic and healthy voices in both databases with speakers suffering from LP. The results obtained in this study suggest that it is not suitable to use every kind of features to model all of the voice pathologies; conversely, it is necessary to study the physiology of each impairment to choose the most appropriate set of features.