Machine learning

Language independent assessment of motor impairments of patients with Parkinson’s disease using i-vectors

Speech disorders are among the most common symptoms in patients with Parkinson’s disease. In recent years, several studies have aimed to analyze speech signals to detect and to monitor the progression of the disease. Most studies have analyzed …

On the impact of non-modal phonation on phonological features

Different modes of vibration of the vocal folds contribute significantly to the voice quality. The neutral mode phonation, often used in a modal voice, is one against which the other modes can be contrastively described, also called non-modal …

Parkinson's disease and aging: analysis of their effect in phonation and articulation of speech

Parkinson’s disease (PD) is a neurological disorder that affects the communication ability of patients. There is interest in the research community to study acoustic measures that provide objective information to model PD speech. Although there are …

Phonation and Articulation Analyses in Laryngeal Pathologies, Cleft Lip and Palate, and Parkinson’s Disease

This study considers phonation and articulation measures to model voice disorders produced by three different pathologies: Laryngeal pathologies (LP), cleft lip and palate (CLP), and Parkinson’s disease (PD). Different speech tasks are considered …

Speaker Model to Monitor the Neurological State and the Dysarthria Level of Patients with Parkinson’s Disease

The progression of the disease in Parkinson’s patients is commonly evaluated with the unified Parkinson’s disease rating scale (UPDRS), which contains several items to assess motor and non–motor impairments. The patients develop speech impairments …

Automatic detection of hypernasal speech of children with cleft lip and palate from spanish vowels and words using classical measures and nonlinear analysis

This paper presents a system for the automatic detection of hypernasal speech signals based on the combination of two different characterization approaches applied to the five Spanish vowels and two selected words. First one is based on classical …

Emotion recognition from speech with acoustic, non-linear and wavelet-based features extracted in different acoustic conditions

In the last years, there has a great progress in automatic speech recognition. The challenge now it is not only recognize the semantic content in the speech but also the called 'paralinguistic' aspects of the speech, including the emotions, and the …

Gender-dependent gmm-ubm for tracking parkinson's disease progression from speech

Parkinson’s disease (PD) severity is evaluated by neurologist experts by means of several tests. One of them is the Movement Disorder Society–Unified Parkinson’s Disease Rating Scale (MDS–UPDRS). The main hypothesis is that changes in the speech of …

Non-linear dynamics characterization from wavelet packet transform for automatic recognition of emotional speech

A new set of features based on non-linear dynamics measures obtained from the wavelet packet transform for the automatic recognition of “fear-type” emotions in speech is proposed. The experiments are carried out using three different databases with a …

Parkinson's Disease Progression Assessment from Speech Using GMM-UBM.

Gaussian Mixture Model Universal Background Model (GMM-UBM) approach is used to assess the Parkinson’s disease (PD) progression per speaker. The disease progression is assessed individually per patient following a user modeling-approach. Voiced and …