Prosodic analysis of neutral, stress-modified and rhymed speech in patients with Parkinson's disease

Galáž, Zoltán; Mekyska, Jiří; Mzourek, Zdenek; Smékal, Zdeněk; Rektorová, Irena; Eliasova, Ilona; Košťálová, Milena; Mračková, Martina; Beránková, Dagmar

doi:10.1016/j.cmpb.2015.12.011

Cited by 66 publications

(49 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…27 Disturbance to speech prosody (stress, intonation, rhythm of speech) is also described as a strong feature. [39][40][41] PwPD report the frustrations of listeners seeming to misunderstand or miss the emotion they are aiming to convey, or the constant feeling that people believe them to be depressed, disinterested, and unmotivated when they are not. [42][43][44] Such impressions are reinforced by hypomimia.…”

Section: Pwpd Perspectives On Change In Speech and Voicementioning

confidence: 99%

<p>Voice treatment in Parkinson’s disease: patient perspectives</p>

Gillivan-Murphy¹,

Miller²,

Carding³

2019

JPRLS

View full text Add to dashboard Cite

Speech and voice changes are a central feature of the symptom complex of people with Parkinson's disease (pwPD). Speaking is a social activity involving the pwPD, family, and the wider communicative context. Sensory-motor, cognitive-linguistic, and affective changes in Parkinson's disease (PD) combine to alter communication, impacting on psychosocial quality-of-life, leading to risks of social withdrawal and increased depression and anxiety. The underlying pathophysiology of speech, voice, and communication difficulties in pwPD is multi-factorial and complex. Sensory-motor changes in the respiratory, phonatory, and articulatory subsystems, underscaling of effort, and central processing problems are further affected by broader cognitive-linguistic difficulties, and non-speech motor deficits. Many studies show that, when pwPD are asked to rate their own voice and how it functions in everyday situations, they show increased voice-related disability and negative impact relative to healthy controls. Voice treatment is integral to improving communication in pwPD. Studies show positive benefits from the perspective of pwPD and carers. Treatment approaches vary from one-to-one to group interventions, a singular focus on increasing loudness to more general voice exercises, and choral singing. The nature and underlying pathophysiology of speech, voice, and communication changes in pwPD are reviewed before exploring the effects of voice treatment programs and pwPD and carer perceptions of their effect. Larger scale, better powered, controlled trials of intervention for voice and speech that measure clinically and socially relevant outcomes are finally underway. Future research should also focus on issues of treatment compliance, practicality (for service delivery and use), and long-term follow-up outcomes. The role of carers in longer-term maintenance represents a further important area of exploration.

show abstract

Section: Pwpd Perspectives On Change In Speech and Voicementioning

confidence: 99%

<p>Voice treatment in Parkinson’s disease: patient perspectives</p>

Gillivan-Murphy¹,

Miller²,

Carding³

2019

JPRLS

View full text Add to dashboard Cite

show abstract

“…Nevertheless, there is still space for deeper investigation. In our previous studies [5], [20], [24] of HD in PD we mainly focused on HD quantification and identification. In our future studies we will follow our recent research in the field of objective assessment of PD [25] and focus on increasing prediction accuracy of several scales developed to rate motor (freezing of gait) and non-motor (depression, sleeping disorders, cognitive impairment) symptoms of PD.…”

Section: Discussionmentioning

confidence: 99%

“…In total, we extracted 715 features. Further description of the features can be found in our recent articles [4], [5], [20]. The exact features selected for each group of speech tasks separately and for whole corpus are shown in Table I.…”

Section: B Speech Features Extractionmentioning

confidence: 99%

See 1 more Smart Citation

Degree of Parkinson's disease severity estimation based on speech signal processing

Galáž

Mzourek

Mekyska

et al. 2016

2016 39th International Conference on Telecommunications and Signal Processing (TSP)

Self Cite

View full text Add to dashboard Cite

This paper deals with Parkinson's disease (PD) severity estimation according to the Unified Parkinson's Disease Rating Scale: motor subscale (UPDRS III), which quantifies the hallmark symptoms of PD, using an acoustic analysis of speech signals. Experimental dataset comprised 42 speech tasks acquired from 50 PD patients (UPDRS III ranged from 6 to 92). It was divided into subsets: words, sentences, reading text, monologue and diadochokinetic tasks. We performed a parametrization of the whole corpus and these groups separately using a wide range of conventional and novel speech features. We used guided regularized random forest algorithm to select features with maximum clinical information and performed random forests regression to estimate PD severity. According to significant correlations between true UPDRS III scores and scores predicted by the proposed methodology it was shown that information extracted through variety of speech tasks can be used to estimate the degree of PD severity.

show abstract

“…As for feature transformation, the frequently used algorithms are PCA (principle component analysis) [26, 27, 31, 49]. As for feature selection, the frequently used algorithms are NN (neural network) based [27–30, 32, 49], serial search based [2, 14, 29, 31], random based [32, 33, 48], p value based [2, 27–34], relevance based [35, 36] or entropy based [37], discrimination algorithm (DA) based [47]. As for classifier design, the predominantly used classifiers include a support vector machine (SVM) [1, 2, 14, 29, 32, 35, 38–41], KNN [1, 2, 26, 28, 40, 41, 47, 48, 49], random forest (RF) [2, 30, 36], Bayesian network [27, 28, 40, 42, 43, 48], discrimination algorithm (DA) [27, 29, 31, 37], probabilistic neural network (PNN) [27, 43] or decision tree [31, 40, 42, 44–46].…”

Section: Introductionmentioning

confidence: 99%

Classification of Parkinson’s disease utilizing multi-edit nearest-neighbor and ensemble learning algorithms with speech samples

et al. 2016

View full text Add to dashboard Cite

BackgroundThe use of speech based data in the classification of Parkinson disease (PD) has been shown to provide an effect, non-invasive mode of classification in recent years. Thus, there has been an increased interest in speech pattern analysis methods applicable to Parkinsonism for building predictive tele-diagnosis and tele-monitoring models. One of the obstacles in optimizing classifications is to reduce noise within the collected speech samples, thus ensuring better classification accuracy and stability. While the currently used methods are effect, the ability to invoke instance selection has been seldomly examined.MethodsIn this study, a PD classification algorithm was proposed and examined that combines a multi-edit-nearest-neighbor (MENN) algorithm and an ensemble learning algorithm. First, the MENN algorithm is applied for selecting optimal training speech samples iteratively, thereby obtaining samples with high separability. Next, an ensemble learning algorithm, random forest (RF) or decorrelated neural network ensembles (DNNE), is used to generate trained samples from the collected training samples. Lastly, the trained ensemble learning algorithms are applied to the test samples for PD classification. This proposed method was examined using a more recently deposited public datasets and compared against other currently used algorithms for validation.ResultsExperimental results showed that the proposed algorithm obtained the highest degree of improved classification accuracy (29.44%) compared with the other algorithm that was examined. Furthermore, the MENN algorithm alone was found to improve classification accuracy by as much as 45.72%. Moreover, the proposed algorithm was found to exhibit a higher stability, particularly when combining the MENN and RF algorithms.ConclusionsThis study showed that the proposed method could improve PD classification when using speech data and can be applied to future studies seeking to improve PD classification methods.

show abstract

Prosodic analysis of neutral, stress-modified and rhymed speech in patients with Parkinson's disease

Cited by 66 publications

References 68 publications

<p>Voice treatment in Parkinson’s disease: patient perspectives</p>

<p>Voice treatment in Parkinson’s disease: patient perspectives</p>

Degree of Parkinson's disease severity estimation based on speech signal processing

Classification of Parkinson’s disease utilizing multi-edit nearest-neighbor and ensemble learning algorithms with speech samples

Contact Info

Product

Resources

About