No abstract

The objective of this study is to evaluate the reliability of acoustic voice parameters obtained using smart phone (SP) microphones and investigate the utility of use of SP voice recordings for voice screening. Voice samples of sustained vowel/a/obtained from 118 subjects (34 normal and 84 pathological voices) were recorded simultaneously through two microphones: oral AKG Perception 220 microphone and SP Samsung Galaxy Note3 microphone. Acoustic voice signal data were measured for fundamental frequency, jitter and shimmer, normalized noise energy (NNE), signal to noise ratio and harmonic to noise ratio using Dr. Speech software. Discriminant analysis-based Correct Classification Rate (CCR) and Random Forest Classifier (RFC) based Equal Error Rate (EER) were used to evaluate the feasibility of acoustic voice parameters classifying normal and pathological voice classes. Lithuanian version of Glottal Function Index (LT_GFI) questionnaire was utilized for self-assessment of the severity of voice disorder. The correlations of acoustic voice parameters obtained with two types of microphones were statistically significant and strong (r = 0.73-1.0) for the entire measurements. When classifying into normal/pathological voice classes, the Oral-NNE revealed the CCR of 73.7% and the pair of SP-NNE and SP-shimmer parameters revealed CCR of 79.5%. However, fusion of the results obtained from SP voice recordings and GFI data provided the CCR of 84.60% and RFC revealed the EER of 7.9%, respectively. In conclusion, measurements of acoustic voice parameters using SP microphone were shown to be reliable in clinical settings demonstrating high CCR and low EER when distinguishing normal and pathological voice classes, and validated the suitability of the SP microphone signal for the task of automatic voice analysis and screening.

The aim of the study was to analyze and quantify the voice characteristics of reflux laryngitis (RL) patients and to determine the most important voice tests and voice-quality parameters in the functional diagnostics of RL. The voices of 83 RL patients and 31 persons in the control group were evaluated. Vocal function was assessed using a multidimensional set of video laryngostroboscopic, perceptual, acoustic, aerodynamic and subjective measurements according to the protocol elaborated by the Committee on Phoniatrics of the European Laryngological Society. The mean values of the hoarseness visual analogue scale assessment and voice handicap index were significantly higher (P<0.05) in the group of RL patients as compared to the controls. Objective voice assessment revealed a significant increase in mean values of jitter, shimmer and normalized noise energy (NNE), along with a significant decrease in pitch range, maximum frequency, phonetogram area (S) and maximum phonation time (MPT) in RL patients, both in the male and female subgroups. According to the results of discriminant analysis, the NNE, MPT, S and intensity range were determined as an optimum set for functional diagnostics of RL. The derived function (equation) makes it possible to assign the person to the group of RL patients with an accuracy of 86.7%. The sensitivity and specificity of eight voice parameters were found to be higher than 50%. The results of the present study demonstrate a reduction of phonation capabilities and voice quality in RL patients. Multidimensional voice evaluation makes it possible to detect significant differences in mean values of perceptual, subjective and objective voice quality parameters between RL patients and controls groups. Therefore, multidimensional voice analysis is an important tool in the functional diagnostics of RL.

No abstract

No abstract