Identification of Smith-Magenis syndrome cases through an experimental evaluation of machine learning methods.

This research work introduces a novel, nonintrusive method for the automatic identification of Smith-Magenis syndrome, traditionally studied through genetic markers. The method utilizes cepstral peak prominence and various machine learning techniques, relying on a single metric computed by the research group. The performance of these techniques is evaluated across two case studies, each employing a unique data preprocessing approach. A proprietary data "windowing" technique is also developed to derive a more representative dataset. To address class imbalance in the dataset, the synthetic minority oversampling technique (SMOTE) is applied for data augmentation. The application of these preprocessing techniques has yielded promising results from a limited initial dataset. The study concludes that the k-nearest neighbors and linear discriminant analysis perform best, and that cepstral peak prominence is a promising measure for identifying Smith-Magenis syndrome.

A Methodology to Differentiate Parkinson's Disease and Aging Speech Based on Glottal Flow Acoustic Analysis.

Speech is controlled by axial neuromotor systems, therefore, it is highly sensitive to the effects of neurodegenerative illnesses such as Parkinson's Disease (PD). Patients suffering from PD present important alterations in speech, which are manifested in phonation, articulation, prosody, and fluency. These alterations may be evaluated using statistical methods on features obtained from glottal, spectral, cepstral, or fractal descriptions of speech. This work introduces an evaluation paradigm based on Information Theory (IT) to differentiate the effects of PD and aging on glottal amplitude distributions. The study is conducted on a database including 48 PD patients (24 males, 24 females), 48 age-matched healthy controls (HC, 24 males, 24 females), and 48 mid-age normative subjects (NS, 24 males, 24 females). It may be concluded from the study that Hierarchical Clustering (HiCl) methods produce a clear separation between the phonation of PD patients from NS subjects (accuracy of 89.6% for both male and female subsets), but the separation between PD patients and HC subjects is less efficient (accuracy of 75.0% for the male subset and 70.8% for the female subset). Conversely, using feature selection and Support Vector Machine (SVM) classification, the differentiation between PD and HC is substantially improved (accuracy of 94.8% for the male subset and 92.8% for the female subset). This improvement was mainly boosted by feature selection, at a cost of information and generalization losses. The results point to the possibility that speech deterioration may affect HC phonation with aging, reducing its difference to PD phonation.

Neuromechanical Modelling of Articulatory Movements from Surface Electromyography and Speech Formants.

Speech articulation is produced by the movements of muscles in the larynx, pharynx, mouth and face. Therefore speech shows acoustic features as formants which are directly related with neuromotor actions of these muscles. The first two formants are strongly related with jaw and tongue muscular activity. Speech can be used as a simple and ubiquitous signal, easy to record and process, either locally or on e-Health platforms. This fact may open a wide set of applications in the study of functional grading and monitoring neurodegenerative diseases. A relevant question, in this sense, is how far speech correlates and neuromotor actions are related. This preliminary study is intended to find answers to this question by using surface electromyographic recordings on the masseter and the acoustic kinematics related with the first formant. It is shown in the study that relevant correlations can be found among the surface electromyographic activity (dynamic muscle behavior) and the positions and first derivatives of the first formant (kinematic variables related to vertical velocity and acceleration of the joint jaw and tongue biomechanical system). As an application example, it is shown that the probability density function associated to these kinematic variables is more sensitive than classical features as Vowel Space Area (VSA) or Formant Centralization Ratio (FCR) in characterizing neuromotor degeneration in Parkinson's Disease.

Improving Speaker Recognition by Biometric Voice Deconstruction.

Person identification, especially in critical environments, has always been a subject of great interest. However, it has gained a new dimension in a world threatened by a new kind of terrorism that uses social networks (e.g., YouTube) to broadcast its message. In this new scenario, classical identification methods (such as fingerprints or face recognition) have been forcedly replaced by alternative biometric characteristics such as voice, as sometimes this is the only feature available. The present study benefits from the advances achieved during last years in understanding and modeling voice production. The paper hypothesizes that a gender-dependent characterization of speakers combined with the use of a set of features derived from the components, resulting from the deconstruction of the voice into its glottal source and vocal tract estimates, will enhance recognition rates when compared to classical approaches. A general description about the main hypothesis and the methodology followed to extract the gender-dependent extended biometric parameters is given. Experimental validation is carried out both on a highly controlled acoustic condition database, and on a mobile phone network recorded under non-controlled acoustic conditions.