Hilbert spectrum analysis for automatic detection and evaluation of Parkinson’s speech

Telemonitoring of Parkinson’s Disease (PD) has attracted considerable research interest because of its potential to make a lasting, positive impact on the life of patients and their carers. Purpose-built devices have been developed that record various signals which can be associated with average PD symptom severity, as quantified on standard clinical metrics such as the Unified Parkinson’s Disease Rating Scale (UPDRS). Speech signals are particularly promising in this regard, because they can be easily recorded without the use of expensive, dedicated hardware. Previous studies have demonstrated replication of UPDRS to within less than 2 points of a clinical raters’ assessment of symptom severity, using high-quality speech signals collected using dedicated telemonitoring hardware. Here, we investigate the potential of using the standard voice-over-GSM (2G) or UMTS (3G) cellular mobile telephone networks for PD telemonitoring, networks that, together, have greater than 5 billion subscribers worldwide. We test the robustness of this approach using a simulated noisy mobile communication network over which speech signals are transmitted, and approximately 6000 recordings from 42 PD subjects. We show that UPDRS can be estimated to within less than 3.5 points difference from the clinical raters’ assessment, which is clinically useful given that the inter-rater variability for UPDRS can be as high as 4–5 UPDRS points. This provides compelling evidence that the existing voice telephone network has potential towards facilitating inexpensive, mass-scale PD symptom telemonitoring applications.

/pdf/remote-assessment-of-parkinson-s-disease-symptom-severity-3x5piusqgq.pdf

Remote Assessment of Parkinson’s Disease Symptom Severity Using the Simulated Cellular Mobile Telephone Network

Residual Neural Network precisely quantifies dysarthria severity-level based on short-duration speech segments.

Principal component analysis of the spectrogram of the speech signal: Interpretation and application to dysarthric speech

We consider the task of speech based classification of patients with amyotrophic lateral sclerosis (ALS), Parkinson’s disease (PD) and healthy controls (HC). Recent work in convolutional neural networks (CNN) to solve image classification problems raises the possibility of utilizing spectral representation of speech for detection of neurological diseases. In this paper, a spectrogram based approach is used. Feeding overlapping windows to the CNN makes sure that the temporal aspects are considered by using short signal segments or wide analysis filters. A three class (ALS, PD or HC) dysarthria classification is performed. In addition, we perform two severity classification experiments for ALS (5 class) and PD (3 class) respectively. Experiments are conducted on both baseline MFCC data [1] and log Mel spectrograms. Classification results show that for several audio lengths, models trained on log Mel spectrograms consistently outperform those of MFCC’s. The ability of the network to accurately classify different classes is evaluated via the area under receiver operating characteristic curve [2],[3]. The findings from this study could aid in better detection and monitoring of ALS and PD diseases.

Speech task based automatic classification of ALS and Parkinson’s Disease and their severity using log Mel spectrograms

Characterization of Parkinson’s disease dysarthria in terms of speech articulation kinematics

Emotion detection is a hot topic nowadays for its potential application to intelligent systems in different fields such as neuromarketing, dialogue systems, friendly robotics, vending platforms and amiable banking. Nevertheless, the lack of a benchmarking standard makes it difficult to compare results produced by different methodologies, which could help the research community improve existing approaches and design new ones. Besides, there is the added problem of accurate dataset production. Most of the emotional speech databases and associated documentation are either privative or not publicly available. Therefore, in this work, two stress-elicited databases containing speech from male and female speakers were recruited, and four classification methods are compared in order to detect and classify speech under stress. Results from each method are presented to show their quality performance, besides the final scores attained, in what is a novel approach to the field of study.

An ICA-based method for stress classification from voice samples

Acoustic to kinematic projection in Parkinson’s disease dysarthria

Patients affected by Amyotrophic Lateral Sclerosis (ALS) show specific dysarthric clues in speech. These marks could be used to detect early symptoms and monitor the evolution of the disease in time. Classically articulation marks have been mainly based on static premises. Articulation Kinematics from acoustic correlates may help in producing measurements based on the dynamic behavior of speech. Specifically, distribution functions from the absolute kinematic velocity estimated by a simplified articulation model can be used in establishing distances based on Information Theory concepts between running speech segments from patients and controls. As an example, a longitudinal case of ALS has been studied using this methodology. It shows that the performance of dynamic articulation quality correlates may be more sensitive and robust than static ones. Conclusions foresee the use of speech as a valuable monitoring methodology for ALS timely evolution.

Articulation acoustic kinematics in ALS speech

Parkinson Disease (PD) is a neuromotor illness affecting general movements of different muscles, those implied in speech production being among them. The relevance of speech in monitoring illness progression has been documented in these last two decades. Most of the studies have concentrated in dysarthria and dysphonia induced by the syndrome. The present work is devoted to explore how PD affects the dynamic behavior of the speech neuromotor biomechanics (neuromechanics) involved in deficient articulation (dysarthria), in contrast to classical measurements based on static features as extreme and central vowel triangle positions. A statistical distribution of the kinematic velocity of the lower jaw and tongue is introduced, which presents interesting properties regarding pattern recognition and classification. This function may be used to establish distances between different articulation profiles in terms of information theory. Results show that these distances are correlated with a set of tests currently used by neurologists in PD progress evaluation, and could be used in elaborating new speech testing protocols.

/pdf/monitoring-parkinson-disease-from-speech-articulation-88e9mk54sv.pdf

Andrés Gómez

Papers

Characterization of Parkinson’s disease dysarthria in terms of speech articulation kinematics

An ICA-based method for stress classification from voice samples

Acoustic to kinematic projection in Parkinson’s disease dysarthria

Articulation acoustic kinematics in ALS speech

Monitoring Parkinson Disease from speech articulation kinematics