https://www.mdu.se/

Speech impairment is an important symptom of Parkinson’s disease (PD). This paper presents a detailed systematic literature review on speech impairment assessment through mobile devices. A two-tier review methodology is utilized. The first tier focuses on real-time problems in speech detection. In the second tier, acoustics features that respond to medication changes in Levodopa responsive PD patients are investigated for recognition of speech symptoms. The investigation of the patents reveals that speech disorder assessment can be made by a comparative analysis between pathological acoustic patterns and the normal acoustic patterns saved in a database. The review depicts that vowel and consonant formants are the most relevant acoustic parameters to reflect PD medication changes. Since consonants have high zero-crossing rate (ZCR) whereas vowels have low ZCR, enhancements in voice segmentation can be done by inducing ZCR. Our synthesis further suggests that wavelet transforms have potential for being useful in real-time voice analysis for detection and quantification of symptoms at home.

Background:The mel-frequency cepstral coefficients (MFCC) are relied for their capability to identify pathological speech. The literature suggests that triangular mel-filters that are used in the MFCC calculation provide an approximation of the human auditory perception. This approximation allows quantifying the clinician’s perception of the intelligibility of the patient’s speech that allows mapping between the clinician’s score of the severity of speech symptoms and the actual symptom severity of the patient’s speech. Previous research on speech impairment in Parkinson’s disease(PD) used sustained-phonation and diadochokinesis tests to score symptoms using the unified Parkinson’s disease rating scale motor speech examination (UPDRS-S).

Objectives:The paper aims to utilize MFCC computed from the recordings of running speech examination for classification of the severity of speech symptoms based on the UPDRS-S. The secondary aim was to compare the performance of the MFCC from running-speech, and the MFCC from sustained-phonation and diadochokinesis recordings, in classifying the UPDRS-S levels.

Method:The study involved audio recordings of motor speech examination of 80 subjects, including 60 PD patients and 20 normal controls. Three different running-speech tests, four different sustained-phonation tests and two different diadochokinesis tests were recorded in different occasions from each subject. The vocal performance of each subject was rated by a clinician using the UPDRS-S. A total of 16 MFCC computed separately from the recordings of running-speech, sustained-phonation and diadochokinesis tests were used to train a support vector machine (SVM) for classifying the levels of UPDRS-S severity. The area under the ROC curve (AoC) was used to compare the feasibility of classification models. Additionally, the Guttman correlation coefficient (μ2) and intra-class correlation coefficient (ICC) were used for feature validation.

Results:The experiments on the SVM trained using the MFCC from running-speech samples produced higher AoC (84%and 85%) in classifying the severity levels of UPDRS-S as compared to the AoC produced by the MFCC from sustained-phonation (88% and 77%) and diadochokinesis (77% and 77%) samples in 10-fold cross validation and training-testing schemes respectively. The μ2 between the MFCC from running speech samples and clinical ratings was stronger (μ2 up to 0.7) than the μ2 between the clinical ratings and the MFCC from sustained-phonation and diadochokinesis samples. The ICC of the MFCC from the running-speech samples recorded in different test occasions was stronger as compared to the ICC of the MFCC from sustained-phonation and diadochokinesis samples recorded in different test occasions.

Conclusions:The strong classification ability of running-speech MFCC and SVM, on one hand, supports suitability of this scheme to monitor speech symptoms in PD. Besides, the values of μ2 and ICC suggest that the MFCC from running speech signals are more reliable for scoring speech symptoms as compared to the MFCC from sustained-phonation and diadochokinesis signals

This paper introduces a novel approach, Cepstral Separation Difference (CSD), for quantification of speech impairment in Parkinson's disease (PD). CSD represents a ratio between the magnitudes of glottal (source) and supra-glottal (filter) log-spectrums acquired using the source-filter speech model. The CSD-based features were tested on a database consisting of 240 clinically rated running speech samples acquired from 60 PD patients and 20 healthy controls. The Guttmann (mu2) monotonic correlations between the CSD features and the speech symptom severity ratings were strong (up to 0.78). This correlation increased with the increasing textual difficulty in different speech tests. CSD was compared with some non-CSD speech features (harmonic ratio, harmonic-to-noise ratio and Mel-frequency cepstral coefficients) for speech symptom characterization in terms of consistency and reproducibility. The high intra-class correlation coefficient (>0.9) and analysis of variance indicates that CSD features can be used reliably to distinguish between severity levels of speech impairment. Results motivate the use of CSD in monitoring speech symptoms in PD

A problem in the clinical assessment of running speech in Parkinson's disease (PD) is to track underlying deficits in a number of speech components including respiration, phonation, articulation and prosody, each of which disturbs the speech intelligibility. A set of 13 features, including the cepstral separation difference and Mel-frequency cepstral coefficients were computed to represent deficits in each individual speech component. These features were then used in training a support vector machine (SVM) using n-fold cross validation. The dataset used for method development and evaluation consisted of 240 running speech samples recorded from 60 PD patients and 20 healthy controls. These speech samples were clinically rated using the Unified Parkinson's Disease Rating Scale Motor Examination of Speech (UPDRS-S). The classification accuracy of SVM was 85% in 3 levels of UPDRS-S scale and 92% in 2 levels with the average area under the ROC (receiver operating characteristic) curves of around 91%. The strong classification ability of selected features and the SVM model supports suitability of this scheme to monitor speech symptoms in PD.

Objectives: The rapid finger-tapping test (RFT) is an important method for clinical evaluation of movement disorders, including Parkinson's disease (PD). In clinical practice, the naked-eye evaluation of RFT results in a coarse judgment of symptom scores. We introduce a novel computer-vision (CV) method for quantification of tapping symptoms through motion analysis of index-fingers. The method is unique as it utilizes facial features to calibrate tapping amplitude for normalization of distance variation between the camera and subject.

Methods: The study involved 387 video footages of RFT recorded from 13 patients diagnosed with advanced PD. Tapping performance in these videos was rated by two clinicians between the symptom severity levels (‘0: normal’ to ‘3: severe’) using the unified Parkinson's disease rating scale motor examination of finger-tapping (UPDRS-FT). Another set of recordings in this study consisted of 84 videos of RFT recorded from 6 healthy controls. These videos were processed by a CV algorithm that tracks the index-finger motion between the video-frames to produce a tapping time-series. Different features were computed from this time series to estimate speed, amplitude, rhythm and fatigue in tapping. The features were trained in a support vector machine (1) to categorize the patient group between UPDRS-FT symptom severity levels, and (2) to discriminate between PD patients and healthy controls.

Results: A new representative feature of tapping rhythm, ‘cross-correlation between the normalized peaks’ showed strong Guttman correlation (mu2 = -0.80) with the clinical ratings. The classification of tapping features using the support vector machine classifier and 10-fold cross validation categorized the patient samples between UPDRS-FT levels with an accuracy of 88%. The same classification scheme discriminated between RFT samples of healthy controls and PD patients with an accuracy of 95%.

Conclusion: The work supports the feasibility of the approach, which is presumed suitable for PD monitoring in the home environment. The system offers advantages over other technologies (e.g. magnetic sensors, accelerometers, etc.) previously developed for objective assessment of tapping symptoms.

Gait disturbance is an important symptom of Parkinson’s disease (PD). This paper presents a review of patents reported in the area of computerized gait disorder analysis. The feasibility of marker-less vision based systems has been examined for ‘at-home’ self-evaluation of gait taking into account the physical restrictions of patients arising due to PD. A three tier review methodology has been utilized to synthesize gait applications to investigate PD related gait features and to explore methods for gait classification based on symptom severities. A comparison between invasive and non-invasive methods for gait analysis revealed that marker-free approach can provide resource efficient, convenient and accurate gait measurements through the use of image processing methods. Image segmentation of human silhouette is the major challenge in the marker-free systems which can possibly be comprehended through the use of Microsoft Kinect application and motion estimation algorithms. Our synthesis further suggests that biorhythmic features in gait patterns have potential to discriminate gait anomalies based on the clinical scales.

This paper presents a computer-vision based marker-free method for gait-impairment detection in Patients with Parkinson’s disease (PWP). The system is based upon the idea that a normal human body attains equilibrium during the gait by aligning the body posture with Axis-of-Gravity (AOG) using feet as the base of support. In contrast, PWP appear to be falling forward as they are less-able to align their body with AOG due to rigid muscular tone. A normal gait exhibits periodic stride-cycles with stride-angle around 45o between the legs, whereas PWP walk with shortened stride-angle with high variability between the stride-cycles. In order to analyze Parkinsonian-gait (PG), subjects were videotaped with several gait-cycles. The subject’s body was segmented using a color-segmentation method to form a silhouette. The silhouette was skeletonized for motion cues extraction. The motion cues analyzed were stride-cycles (based on the cyclic leg motion of skeleton) and posture lean (based on the angle between leaned torso of skeleton and AOG). Cosine similarity between an imaginary perfect gait pattern and the subject gait patterns produced 100% recognition rate of PG for 4 normal-controls and 3 PWP. Results suggested that the method is a promising tool to be used for PG assessment in home-environment.