MonParLoc: A Speech-Based System for Parkinson’s Disease Analysis and Monitoring

Abstract

Patients suffering from Parkinson's Disease (PD) manifest relevant changes in their speech, consisting of specific landmarks in articulation, phonation, fluency, and prosody. Usually, phonation and articulation changes are estimated and evaluated using different methods and statistical frameworks. Speech is especially relevant as a vehicular mechanism to monitor neurological evolution using well-known features extracted from sustained phonations (mainly vowels), diadochokinetic exercises, or running speech. Recent studies have shown that acoustic neurostimulation using binaural beats influences the cognitive and neuromotor conditions of patients with PD, at least temporarily after stimulation. The aim of this study is to describe an added-value solution considering the cooperation of both previously mentioned methods: speech analysis-based monitoring called within the project, Monitoring Parkinson using Locution (MonParLoc), and acoustical neurostimulation, called within project neuro-Acoustic-stimulation Parkinson (AcousticPar). The applications designed in both projects are embedded into a global solution denominated Teca-Park which consists of four main activities: speech evaluation, neurostimulation, motor symptom longitudinally, and questionnaires. This framework is conceived to be a powerful tool for treating and monitoring longitudinally remotely and contact-free. MonParLoc was tested and validated in real scenarios involving patient associations. Validation results produced in these associations demonstrating the utility of this approach are given in the study, particularly in reference to protocol vulnerability and robustness. This paper proposes a complete framework (a mobile app and a scorecard solution) including different services for Parkinson's clinical monitoring and patient management using speech, movement, and acoustic stimulation.

A Neuromotor to Acoustical Jaw-Tongue Projection Model With Application in Parkinson’s Disease Hypokinetic Dysarthria

“…Once the projection model is validated using the multi-trait signals (speech, sEMG and 3DAcc) the detection properties of the proposed biomarkers (AKV and AFV) will be tested on larger PD speech databases (Sakar et al, 2013;Orozco-Arroyave et al, 2014), however, as they only contain speech data, we cannot use them for this validation phase, considering the novel direction that this work is proposing. Hopefully we will be able of using the projection model to produce the AKV and AFV biomarkers, to validate the statistical relevance of a speechbased home-monitoring approach on these databases and others recruited by our own using a tele-health platform (see Palacios et al, 2020). Another limiting factor is that PD participants were in a moderate stage of motor activity deterioration (H&Y stage 2).…”

“…The estimates of the acoustic accelerations a fx and a fy help in establishing a validation for the indirect estimation of kinematic variables directly from acoustics. These kinematic variables would allow estimating the neuromotor activity directly from acoustics using speech recordings from remote devices (Palacios et al, 2020).…”

Gait monitoring system for patients with Parkinson’s disease

“…Given the mass use of smartphones, the number of smart applications for motor monitoring in PD increased over the last years (Linares-del Rey, Vela-Desojo, & Canode la Cuerda, 2019). Advances included to monitor speech and tremor besides to provide gait analysis (Palacios-Alonso et al, 2020).…”

Acoustic Analysis of Phonation in Children With Smith–Magenis Syndrome

“…Many studies have examined the neuromotor profile of the speech of populations with Parkinson, amyotrophic lateral sclerosis (ALS), cerebral palsy, hydrocephalus, among others, showing that speech production and phonation are compromised in the presence of diseases of neurological origin ( Palacios-Alonso et al, 2020 ).…”