Characterisation of voice quality of Parkinson’s disease using differential phonological posterior features

Abstract

Change in voice quality (VQ) is one of the first precursors of Parkinson's disease (PD). Specifically, impacted phonation and articulation causes the patient to have a breathy, husky-semiwhisper and hoarse voice.A goal of this paper is to characterize a VQ spectrum -the composition of non-modal phonations -of voice in PD. The paper relates non-modal healthy phonations: breathy, creaky, tense, falsetto and harsh, with disordered phonation in PD. First, statistics are learned to differentiate the modal and non-modal phonations. Statistics are computed using phonological posteriors, the probabilities of phonological features inferred from the speech signal using a deep learning approach. Second, statistics of disordered speech are learned from PD speech data comprising 50 patients and 50 healthy controls. Third, Euclidean distance is used to calculate similarity of non-modal and disordered statistics, and the inverse of the distances is used to obtain the composition of non-modal phonation in PD. Thus, pathological voice quality is characterised using healthy non-modal voice quality "base/eigenspace". The obtained results are interpreted as the voice of an average patient with PD and can be characterised by the voice quality spectrum composed of 30% breathy voice, 23% creaky voice, 20% tense voice, 15% falsetto voice and 12% harsh voice. In addition, the proposed features were applied for prediction * Corresponding author Email address: milos.cernak@idiap.ch (Milos Cernak) of the dysarthria level according to the Frenchay assessment score related to the larynx, and significant improvement is obtained for reading speech task. The proposed characterisation of VQ might also be applied to other kinds of pathological speech.

Articulation and Empirical Mode Decomposition Features in Diadochokinetic Exercises for the Speech Assessment of Parkinson’s Disease Patients

“…Similarly to the classification experiments, the highest correlation is obtained with the combination of transition and regularity features (ρ=0.6782). The "strong" correlation obtained is statistically significant, and it is comparable to the obtained in related studies, where the same problem was addressed [14,18].…”

Detecting Parkinson’s disease with sustained phonation and speech signals using machine learning techniques

“…In 2013, sustained vowels, words, and sentences from a set of speaking tasks were found to carry PDdiscriminative information that can be utilized using machine learning tools [11]. The works using voice signal continued in the following years with the contribution of new feature extractors and new data sets [12,13,14]. The most notable trends are: the use of smartphone technology for the recording of speech samples in everyday life, capturing signs of speech impairment in persons [15], and the development of software for analysing pathological speech signals, taking into account phonation, articulation, prosody, and intelligibility.…”

Automated Cross-language Intelligibility Analysis of Parkinson’s Disease Patients Using Speech Recognition Technologies

“…The proposed model will be able to identify specific aspects in the speech related to the pronunciation of consonants, which are the most affected aspects of the speech of the patients due to the disease. The segmentation process will be performed using a trained model to detect phonological classes, like those ones used in the previous studies (Vásquez-Correa et al, 2019;Cernak et al, 2017). Figure 3 shows the possible differences in articulation and phonation in PD and HC subjects.…”