Phonation and Articulation Analysis of Spanish Vowels for Automatic Detection of Parkinson’s Disease

Orozco-Arroyave, Juan Rafael; Belalcázar-Bolaños, Elkyn Alexander; Arias-Londoño, Julián D.; Vargas-Bonilla, Jesús Francisco; Haderlein, Tino; Nöth, Elmar

doi:10.1007/978-3-319-10816-2_45

Cited by 12 publications

(14 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The results presented in this paper indicate that depression affect speech motor control. The reductions in spectral variability match the intensity decay reported for dysarthric speech (Kent and Kim, 2003), and the reductions in acoustic variability measures match with the reductions in vowel space reported in both dysarthric speech (McRae et al, 2002;Orozco-Arroyave et al, 2014;Sapir et al, 2010) and speech affected by depression . Future research will involve testing the acoustic variability measures on conditions which may affect speech motor control, including Parkinson's disease, post-traumatic stress disorder and suicidality.…”

Section: Resultssupporting

confidence: 71%

“…VSA is usually constructed by the Euclidean distances between the F1 and F2 coordinates of the corner vowels /i/, /u/, and /a/ (Skodda et al, 2012). Significantly smaller vowel space is often reported in the literature when comparing speech affected by Parkinson's disease to speech from matched healthy subjects (McRae et al, 2002;Orozco-Arroyave et al, 2014;Sapir et al, 2010). However VSA is known to be sensitive to sensitive to inter-speaker variability, recording environment and method of formant extraction (Sapir et al, 2010).…”

Section: Related Speech Motor Control Disordersmentioning

confidence: 99%

See 1 more Smart Citation

Analysis of acoustic space variability in speech affected by depression

Cummins

Sethu

Epps

et al. 2015

Speech Communication

View full text Add to dashboard Cite

The spectral and energy properties of speech have consistently been observed to change with a speaker's level of clinical depression. This has resulted in spectral and energy based features being a key component in many speech-based classification and prediction systems. However there has been no in-depth investigation into understanding how acoustic models of spectral features are affected by depression. This paper investigates the hypothesis that the effects of depression in speech manifest as a reduction in the spread of phonetic events in acoustic space as modelled by Gaussian Mixture Models (GMM) in combination with Mel Frequency Cepstral Coefficients (MFCC).Our investigation uses three measures of acoustic variability: Average Weighted Variance (AWV), Acoustic Movement (AM) and Acoustic Volume, which attempt to model depression specific acoustic variations (AWV and Acoustic Volume), or the trajectory of a speech in the acoustic space (AM).Within our analysis we present the Probabilistic Acoustic Volume (PAV) a novel method for robustly estimating Acoustic Volume using a Monte Carlo sampling of the feature distribution being * Corresponding Author modelled. We show that using an array of PAV points we gain insights into how the concentration of the feature vectors in the feature space changes with depression. Key results -found on two commonly used depression corpora -consistently indicate that as a speaker's level of depression increases there are statistically significantly reductions in both AWV (-0.44 ≤ r s ≤ -0.18 with p < .05) and AM (-0.26 ≤ r s ≤ -0.19 with p < .05) values, indicating a decrease in localised acoustic variance and smoothing in acoustic trajectory respectively. Further there are also statistically significant reductions (-0.32 ≤ r s ≤ -0.20 with p < .05) in Acoustic Volume measures and strong statistical evidence (-0.48 ≤ r s ≤ -0.23 with p < .05) that the MFCC feature space becomes more concentrated.Quantifying these effects is expected to be a key step towards building an objective classification or prediction system which is robust to many of the unwanted -in terms of depression analysissources of variability modulated into a speech signal.

show abstract

Section: Resultssupporting

confidence: 71%

Section: Related Speech Motor Control Disordersmentioning

confidence: 99%

Analysis of acoustic space variability in speech affected by depression

Cummins

Sethu

Epps

et al. 2015

Speech Communication

View full text Add to dashboard Cite

show abstract

“…These findings indicate that speech affected by depression can be characterised by a reduction in the number of distinct speech sounds produced and a reduction in overall speaking effort and animation. Further, they provide strong evidence that depression should be considered a speech motor control disorder; similar characterizations are found in the appropriate literature [McRae et al, 2002;Orozco-Arroyave et al, 2014;Sapir et al, 2010].…”

Section: Speech Analysissupporting

confidence: 71%

Multimodal assessment of depression from behavioral signals

Cohn¹,

Cummins²,

Epps³

et al. 2018

The Handbook of Multimodal-Multisensor Interfaces: Foundations, User Modeling, and Common Modality Combinations - Volume 2

View full text Add to dashboard Cite

Reliable, valid, and efficient assessment of depression is critical to identify individuals in need of treatment and to gauge treatment response. Current methods of assessment are limited to subjective measures of patient self-report and clinical interview. They fail to take into account observable measures of behavior that could better inform detection of the occurrence and severity of depression. Recent advances in computer vision, signal processing, and machine learning have potential to meet the need for improved depression screening, diagnosis, and ascertainment of severity (i.e., assessment). This chapter reviews these advances. We describe multimodal measures of behavior and physiology, how these measures can be processed to extract features sensitive to depression, and how classification or prediction may be used to provide automatic assessment of depression occurrence and severity. Following an overview in Sections 2 of how behavioral and physiological sensor signals can be processed in a multimodal manner, Sections 3 to 6 discuss in detail how to extract features sensitive to depression, based on insights from earlier scientific investigations and from studies of existing clinical assessment. These latter Sections also touch on key machine learning methods that have been adopted to date. Of particular interest is the fusion of information from different modalities, and Section 7 discusses fusion in the context of both classification and prediction. For researchers investigating automatic analysis of depression, high quality research data is a critical concern. Similarly important for the practical application of multimodal depression assessment systems is their likely context of use. Both concerns are discussed in Section 8, while Section 9 provides an overview of key challenges in this research area. In this chapter, the focus is primarily on depression. This emphasis reflects the emphasis in the field. Most work to date on automated, multimodal assessment of psychopathology has focused on depression. Other disorders, such as post-traumatic stress disorder, generalized anxiety disorder, traumatic brain injury, suicidality, dementia, Alzheimer's disease, schizophrenia, Parkinson's disease, and autism spectrum disorder have received less attention and accordingly are not discussed in detail. The approaches and many of the methods we discuss, nevertheless, are applicable to disorders that share behavioral features, are comorbid with depression, or otherwise share variance with depression. Dimensional models of psychopathology [HiTOP, Undated; Kotov, Gamez, Schmidt, & Watson, 2010] in particular group unipolar depression (Major Depressive Disorder and Dysthymia), Generalized Anxiety Disorder, PTSD, and in some models Borderline Personality Disorder together as distress orders. From this perspective, the research we review on depression is relevant to these disorders as well. 1. Depression Depression is one of the most common mental disorders [Kessler, Chiu, Demler, and Walters, 2005] and a leading cause of...

show abstract

“…A limitação de movimentos observada na DP pode levar a constrição do triângulo e uma redução da área do espaço vocálico. Os estudos que utilizaram essas medidas, entretanto, nem sempre conseguiram revelar diferenças significativas entre falantes saudáveis e falantes com DP (BANG et al, 2013;OKADA;MURATA;TODA, 2015;OROZCO-ARROYAVE et al, 2014;SAPIR et al, 2010;SKODDA;VISSER;SCHLEGEL, 2011;TJADEN et al, 2013 Mas a inclusão da frequência fundamental pode ser questionada quando o que se pretende é avaliar a articulação da fala. O estudo longitudinal de Skodda et al (2013), que acompanhou 80 pessoas com DP, observou a deterioração progressiva da voz e da fala no curso da doença e evidenciou que as medidas de shimmer (medida de perturbação na amplitude, ou intensidade, durante a emissão vocal) -e não de jitter (medida de perturbação na frequência fundamental, durante a emissão vocal) -eram significativamente mais altas na DP, desde os estágios iniciais da doença.…”

Section: Introductionunclassified

“…É provável que os valores de intensidade representem uma medida mais robusta para diferenciar a fala na DP e propõe-se a sua inclusão nos parâmetros já existentes por meio de um novo índice, o Índice de Articulação e Intensidade Vocálica, e da construção de um prisma acústico-articulatório, similar ao de Orozco- Arroyave et al (2014), mas que contemple os valores de intensidade (dB) em seu eixo z. Sabe-se que há desafios a superar, pois trata-se de uma medida acústica sujeita a interferências, mas acredita-se que avanços só serão possíveis se esses obstáculos forem enfrentados.…”

Section: Introductionunclassified

Análise Acústica das Vogais Produzidas por Falantes com Doença de Parkinson

Carvalho¹,

Oliveira²

2021

Estudos Em Fonética E Fonologia

View full text Add to dashboard Cite

Phonation and Articulation Analysis of Spanish Vowels for Automatic Detection of Parkinson’s Disease

Cited by 12 publications

References 12 publications

Analysis of acoustic space variability in speech affected by depression

Analysis of acoustic space variability in speech affected by depression

Multimodal assessment of depression from behavioral signals

Análise Acústica das Vogais Produzidas por Falantes com Doença de Parkinson

Contact Info

Product

Resources

About