Study of the Automatic Detection of Parkison's Disease Based on Speaker Recognition Technologies and Allophonic Distillation.

The use of new tools to detect Parkinson's Disease (PD) from speech articulatory movements can have a considerable impact in the diagnosis of patients. In this study, a novel approach involving speaker recognition techniques with allophonic distillation is proposed and tested separately in four parkinsonian speech databases (205 patients and 186 controls in total). This new scheme provides values between 72% and 94% of accuracy in the automatic detection of PD, depending on the database, and improvements up to 9% respect to baseline techniques. Results not only point towards the importance of the segmentation of the speech for the differentiation of parkinsonian and control speakers but confirm previous findings about the relevance of plosives and fricatives in the detection of parkinsonian dysarthria.

Towards the identification of Idiopathic Parkinson's Disease from the speech. New articulatory kinetic biomarkers.

Although a large amount of acoustic indicators have already been proposed in the literature to evaluate the hypokinetic dysarthria of people with Parkinson's Disease, the goal of this work is to identify and interpret new reliable and complementary articulatory biomarkers that could be applied to predict/evaluate Parkinson's Disease from a diadochokinetic test, contributing to the possibility of a further multidimensional analysis of the speech of parkinsonian patients. The new biomarkers proposed are based on the kinetic behaviour of the envelope trace, which is directly linked with the articulatory dysfunctions introduced by the disease since the early stages. The interest of these new articulatory indicators stands on their easiness of identification and interpretation, and their potential to be translated into computer based automatic methods to screen the disease from the speech. Throughout this paper, the accuracy provided by these acoustic kinetic biomarkers is compared with the one obtained with a baseline system based on speaker identification techniques. Results show accuracies around 85% that are in line with those obtained with the complex state of the art speaker recognition techniques, but with an easier physical interpretation, which open the possibility to be transferred to a clinical setting.

Influence of delay time on regularity estimation for voice pathology detection.

The employment of nonlinear analysis techniques for automatic voice pathology detection systems has gained popularity due to the ability of such techniques for dealing with the underlying nonlinear phenomena. On this respect, characterization using nonlinear analysis typically employs the classical Correlation Dimension and the largest Lyapunov Exponent, as well as some regularity quantifiers computing the system predictability. Mostly, regularity features highly depend on a correct choosing of some parameters. One of those, the delay time τ, is usually fixed to be 1. Nonetheless, it has been stated that a unity τ can not avoid linear correlation of the time series and hence, may not correctly capture system nonlinearities. Therefore, present work studies the influence of the τ parameter on the estimation of regularity features. Three τ estimations are considered: the baseline value 1; a τ based on the Average Automutual Information criterion; and τ chosen from the embedding window. Testing results obtained for pathological voice suggest that an improved accuracy might be obtained by using a τ value different from 1, as it accounts for the underlying nonlinearities of the voice signal.

Objective measurements to evaluate glottal space segmentation from laryngeal images.

Objective evaluation of the results of medical image segmentation is a known problem. Applied to the task of automatically detecting the glottal area from laryngeal images, this paper proposes a new objective measurement to evaluate the quality of a segmentation algorithm by comparing with the results given by a human expert. The new figure of merit is called Area Index, and its effectiveness is compared with one of the most used figures of merit found in the literature: the Pratt Index. Results over 110 laryngeal images presented high correlations between both indexes, demonstrating that the proposed measure is comparable to the Pratt Index and it is a good indicator of the segmentation quality.

On improvement of detection of Obstructive Sleep Apnea by partial least square-based extraction of dynamic features.

This paper presents a methodology for Obstructive Sleep Apnea (OSA) detection based on the HRV analysis, where as a measure of relevance PLS is used. Besides, two different combining approaches for the selection of the best set of contours are studied. Attained results can be oriented in research focused on finding alternative methods minimizing the HRV-derived parameters used for OSA diagnosing, with a diagnostic accuracy comparable to a polysomnogram. For two classes (normal, apnea) the results for PLS are: specificity 90%, sensibility 91% and accuracy 93.56%.

Feature extraction from parametric time-frequency representations for heart murmur detection.

The detection of murmurs from phonocardiographic recordings is an interesting problem that has been addressed before using a wide variety of techniques. In this context, this article explores the capabilities of an enhanced time-frequency representation (TFR) based on a time-varying autoregressive model. The parametric technique is used to compute the TFR of the signal, which serves as a complete characterization of the process. Parametric TFRs contain a large quantity of data, including redundant and irrelevant information. In order to extract the most relevant features from TFRs, two specific approaches for dimensionality reduction are presented: feature extraction by linear decomposition, and tiling partition of the t-f plane. In the first approach, the feature extraction was carried out by means of eigenplane-based PCA and PLS techniques. Likewise, a regular partition and a refined Quadtree partition of the t-f plane were tested for the tiled-TFR approach. As a result, the feature extraction methodology presented, which searches for the most relevant information immersed on the TFR, has demonstrated to be very effective. The features extracted were used to feed a simple k-nn classifier. The experiments were carried out using 45 phonocardiographic recordings (26 normal and 19 records with murmurs), segmented to extract 548 representative individual beats. The results using these methods point out that better accuracy and flexibility can be accomplished to represent non-stationary PCG signals, showing evidences of improvement with respect to other approaches found in the literature. The best accuracy obtained was 99.06 +/- 0.06%, evidencing high performance and stability. Because of its effectiveness and simplicity of implementation, the proposed methodology can be used as a simple diagnostic tool for primary health-care purposes.

Selection of dynamic features based on time-frequency representations for heart murmur detection from phonocardiographic signals.

This work discusses a method for the selection of dynamic features, based on the calculation of the spectral power through time applied to the detection of systolic murmurs from phonocardiographic recordings. To investigate the dynamic properties of the spectral power during murmurs, several quadratic energy distributions have been studied, namely Wigner-Ville, Choi-Williams, smoothed pseudo Wigner-Ville, exponential, and hyperbolic T-distribution. The classification performance has been compared with that using a Short Time Fourier Transform and Continuous Wavelet Transform representations. Furthermore, this work discusses a variety of nonparametric techniques to estimate the spectral power contours as dynamic features that characterize the heart sounds (HS): instantaneous energy, eigenvectors, instantaneous frequency, equivalent bandwidth, subband spectral centroids, and Mel cepstral coefficients. In this way, the aforementioned time-frequency representations and their dynamic features were evaluated by means of their ability to detect the presence of murmurs using a simple k-Nearest Neighbors classifier. Moreover, the relevancies of the proposed dynamic features have been evaluated using a time-varying principal component analysis. The work presented is carried out using a database containing 22 phonocardiographic recordings (16 normal and 6 records with murmurs), segmented to extract 402 representative individual beats (201 per class). The results suggest that the smoothing given by the quadratic energy distribution significantly improves the classification performance for the detection of murmurs in HS. Moreover, it is shown that the power dynamic features which give the best overall classification performance are the MFCC contours. As a result, the proposed method can be implemented as a simple diagnostic tool for primary health-care purposes with high accuracy (up to 98%) discriminating between normal and pathologic beats.

Automatic detection of laryngeal pathologies in records of sustained vowels by means of mel-frequency cepstral coefficient parameters and differentiation of patients by sex.

Mel-frequency cepstral coefficients (MFCC) have traditionally been used in speaker identification applications. Their use has been extended to speech quality assessment for clinical applications during the last few years. While the significance of such parameters for such an application may not seem clear at first thought, previous research has demonstrated their robustness and statistical significance and, at the same time, their close relationship with glottal noise measurements. This paper includes a review of this parameterization scheme and it analyzes its performance for voice analysis when patients are differentiated by sex. While it is of common use for establishing normative values for traditional voice descriptors (e.g. pitch, jitter, formants), differentiation by sex had not been tested yet for cepstral analysis of voice with clinical purposes. This paper shows that the automatic detection of laryngeal pathology on voice records based on MFCC can significantly improve its performance by means of this prior differentiation by sex.

Digital auscultation analysis for heart murmur detection.

This work presents a comparison of different approaches for the detection of murmurs from phonocardiographic signals. Taking into account the variability of the phonocardiographic signals induced by valve disorders, three families of features were analyzed: (a) time-varying & time-frequency features; (b) perceptual; and (c) fractal features. With the aim of improving the performance of the system, the accuracy of the system was tested using several combinations of the aforementioned families of parameters. In the second stage, the main components extracted from each family were combined together with the goal of improving the accuracy of the system. The contribution of each family of features extracted was evaluated by means of a simple k-nearest neighbors classifier, showing that fractal features provide the best accuracy (97.17%), followed by time-varying & time-frequency (95.28%), and perceptual features (88.7%). However, an accuracy around 94% can be reached just by using the two main features of the fractal family; therefore, considering the difficulties related to the automatic intrabeat segmentation needed for spectral and perceptual features, this scheme becomes an interesting alternative. The conclusion is that fractal type features were the most robust family of parameters (in the sense of accuracy vs. computational load) for the automatic detection of murmurs. This work was carried out using a database that contains 164 phonocardiographic recordings (81 normal and 83 records with murmurs). The database was segmented to extract 360 representative individual beats (180 per class).

Automatic detection of voice impairments by means of short-term cepstral parameters and neural network based detectors.

It is well known that vocal and voice diseases do not necessarily cause perceptible changes in the acoustic voice signal. Acoustic analysis is a useful tool to diagnose voice diseases being a complementary technique to other methods based on direct observation of the vocal folds by laryngoscopy. Through the present paper two neural-network based classification approaches applied to the automatic detection of voice disorders will be studied. Structures studied are multilayer perceptron and learning vector quantization fed using short-term vectors calculated accordingly to the well-known Mel Frequency Coefficient cepstral parameterization. The paper shows that these architectures allow the detection of voice disorders--including glottic cancer--under highly reliable conditions. Within this context, the Learning Vector quantization methodology demonstrated to be more reliable than the multilayer perceptron architecture yielding 96% frame accuracy under similar working conditions.