Voice Analysis for Neurological Disorder Recognition–A Systematic Review and Perspective on Emerging Trends

Abstract

Quantifying neurological disorders from voice is a rapidly growing field of research and holds promise for unobtrusive and large-scale disorder monitoring. The data recording setup and data analysis pipelines are both crucial aspects to effectively obtain relevant information from participants. Therefore, we performed a systematic review to provide a high-level overview of practices across various neurological disorders and highlight emerging trends. PRISMA-based literature searches were conducted through PubMed, Web of Science, and IEEE Xplore to identify publications in which original (i.e., newly recorded) datasets were collected. Disorders of interest were psychiatric as well as neurodegenerative disorders, such as bipolar disorder, depression, and stress, as well as amyotrophic lateral sclerosis amyotrophic lateral sclerosis, Alzheimer's, and Parkinson's disease, and speech impairments (aphasia, dysarthria, and dysphonia). Of the 43 retrieved studies, Parkinson's disease is represented most prominently with 19 discovered datasets. Free speech and read speech tasks are most commonly used across disorders. Besides popular feature extraction toolkits, many studies utilise custom-built feature sets. Correlations of acoustic features with psychiatric and neurodegenerative disorders are presented. In terms of analysis, statistical analysis for significance of individual features is commonly used, as well as predictive modeling approaches, especially with support vector machines and a small number of artificial neural networks. An emerging trend and recommendation for future studies is to collect data in everyday life to facilitate longitudinal data collection and to capture the behavior of participants more naturally. Another emerging trend is to record additional modalities to voice, which can potentially increase analytical performance.

Using deeply time-series semantics to assess depressive symptoms based on clinical interview speech

“…Studies have found differences between the voices of depressed and healthy people ( 22 ), and acoustic features are correlate with the severity of depressive symptoms and their variability ( 23 ). Several acoustic features are thought to correlate with depression ( 24 ), Machine Learning and Deep Learning techniques have been widely used in the studies of voice analysis ( 25 ). For the audio recordings in this study, we also performed some voice analysis.…”

Ataxic speech disorders and Parkinson’s disease diagnostics via stochastic embedding of empirical mode decomposition

“…., t N . For the squared error loss L(y i , γ l (t i )) = L(y i − γ l (t i )) 2 the solution corresponds to the natural polynomial spline, see discussion in [64]. Hence, we have been able to motivate the spline representation of the IMF as the solution to a generalised estimation problem in an RKHS regularised function space.…”

“…These are repeating syllables, spontaneous dialogue, improvised description of a figure, etc. [ 2 ]. An ASR system can use several speech features descriptive of the different phases of speech production process, extensively reviewed by [ 2 , 4 , 21 , 22 ].…”

“…[ 2 ]. An ASR system can use several speech features descriptive of the different phases of speech production process, extensively reviewed by [ 2 , 4 , 21 , 22 ]. Amongst many, acoustic or vocal tract features describing the articulatory phase are the ones that correlate the most with neurodegenerative disorders.…”

“…Furthermore, the same symptoms manifest in multiple of these conditions [1], demanding expensive equipment and advanced expertise for the correct diagnosis. As a solution, the developments of artificial intelligence in biotechnology have started to support these medical settings with automated computational tools that can increasingly identify disorders' abnormalities in real-life-sensing environments [2][3][4][5]. The challenge in detecting symptoms of such nervous system disorders through a computerised practice is accomplished via several modalities (such as speech, handwriting, radiology, gait, etc.)…”