Analysis of the relationship between emotion intensity and electrophysiology parameters during a voice examination of opera singers.

OBJECTIVES: Emotions and stress affect voice production. There are only a few reports in the literature on how changes in the autonomic nervous system affect voice production. The aim of this study was to examine emotions and measure stress reactions during a voice examination procedure, particularly changes in the muscles surrounding the larynx. MATERIAL AND METHODS: The study material included 50 healthy volunteers (26 voice workers - opera singers, 24 control subjects), all without vocal complaints. All subjects had good voice quality in a perceptual assessment. The research procedure consisted of 4 parts: an ear, nose, and throat (ENT)­phoniatric examination, surface electromyography, recording physiological indicators (heart rate and skin resistance) using a wearable wristband, and a psychological profile based on questionnaires. RESULTS: The results of the study demonstrated that there was a relationship between positive and negative emotions and stress reactions related to the voice examination procedure, as well as to the tone of the vocal tract muscles. There were significant correlations between measures describing the intensity of experienced emotions and vocal tract muscle maximum amplitude of the cricothyroid (CT) and sternocleidomastoid (SCM) muscles during phonation and non-phonation tasks. Subjects experiencing eustress (favorable stress response) had increased amplitude of submandibular and CT at rest and phonation. Subjects with high levels of negative emotions, revealed positive correlations with SCMmax during the glissando. The perception of positive and negative emotions caused different responses not only in the vocal tract but also in the vegetative system. Correlations were found between emotions and physiological parameters, most markedly in heart rate variability. A higher incidence of extreme emotions was observed in the professional group. CONCLUSIONS: The activity of the vocal tract muscles depends on the type and intensity of the emotions and stress reactions. The perception of positive and negative emotions causes different responses in the vegetative system and the vocal tract. Int J Occup Med Environ Health. 2024;37(1):84-97.

Electrophysiological predictors of hyperfunctional dysphonia.

BACKGROUND: The relation between the autonomic nervous system (ANS) and muscles of the vocal tract is of particular importance when considering the pathomechanism of a functional voice disorder. AIMS: The aim of this study was to record electrophysiological indicators from the ANS as well as the tone of the external laryngeal muscle and test whether together they could point to an enhanced risk of primary functional voice disorder. MATERIALS AND METHODS: The study material consisted of 81 people, 27 of whom were professional opera singers. None reported any voice complaints. The research comprised ENT and phoniatric examination, superficial electromyography (SEMG), and recording of physiological indicators (pulse rate, skin resistance). RESULTS: All subjects had a clear voice with no sign of vocal disability. Endoscopy revealed laryngeal hyperfunction in 26 people. SEMG revealed that the 26 had increased external laryngeal muscle tone during phonation, and this finding correlated with a change in certain electrophysiological indicators HRV, BVP, EDA. CONCLUSIONS: We conclude that anomalies in electrophysiological parameters in individuals with subclinical symptoms of functional voice disorder may be at risk of developing fully symptomatic hyperfunctional dysphonia in the future. Vocal training, which differentiates singers and non-singers, is known to have an effect on subclinical hyperfunctional dysphonia. SIGNIFICANCE: By measuring indicators of hyperfunctional dysphonia, it may be possible to take remedial action before symptomatic dysphonia develops.

Real-Time Back Surface Landmark Determination Using a Time-of-Flight Camera.

Postural disorders, their prevention, and therapies are still growing modern problems. The currently used diagnostic methods are questionable due to the exposure to side effects (radiological methods) as well as being time-consuming and subjective (manual methods). Although the computer-aided diagnosis of posture disorders is well developed, there is still the need to improve existing solutions, search for new measurement methods, and create new algorithms for data processing. Based on point clouds from a Time-of-Flight camera, the presented method allows a non-contact, real-time detection of anatomical landmarks on the subject's back and, thus, an objective determination of trunk surface metrics. Based on a comparison of the obtained results with the evaluation of three independent experts, the accuracy of the obtained results was confirmed. The average distance between the expert indications and method results for all landmarks was 27.73 mm. A direct comparison showed that the compared differences were statically significantly different; however, the effect was negligible. Compared with other automatic anatomical landmark detection methods, ours has a similar accuracy with the possibility of real-time analysis. The advantages of the presented method are non-invasiveness, non-contact, and the possibility of continuous observation, also during exercise. The proposed solution is another step in the general trend of objectivization in physiotherapeutic diagnostics.

Affective State during Physiotherapy and Its Analysis Using Machine Learning Methods.

Invasive or uncomfortable procedures especially during healthcare trigger emotions. Technological development of the equipment and systems for monitoring and recording psychophysiological functions enables continuous observation of changes to a situation responding to a situation. The presented study aimed to focus on the analysis of the individual's affective state. The results reflect the excitation expressed by the subjects' statements collected with psychological questionnaires. The research group consisted of 49 participants (22 women and 25 men). The measurement protocol included acquiring the electrodermal activity signal, cardiac signals, and accelerometric signals in three axes. Subjective measurements were acquired for affective state using the JAWS questionnaires, for cognitive skills the DST, and for verbal fluency the VFT. The physiological and psychological data were subjected to statistical analysis and then to a machine learning process using different features selection methods (JMI or PCA). The highest accuracy of the kNN classifier was achieved in combination with the JMI method (81.63%) concerning the division complying with the JAWS test results. The classification sensitivity and specificity were 85.71% and 71.43%.

Adolescent age estimation using voice features.

In this paper, a method for evaluating the chronological age of adolescents on the basis of their voice signal is presented. For every examined child, the vowels a, e, i, o and u were recorded in extended phonation. Sixty voice parameters were extracted from each recording. Voice recordings were supplemented with height measurement in order to check if it could improve the accuracy of the proposed solution. Predictor selection was performed using the LASSO (least absolute shrinkage and selection operator) algorithm. For age estimation, the random forest (RF) for regression method was employed and it was tested using a 10-fold cross-validation. The lowest absolute error (0.37 year ± 0.28) was obtained for boys only when all selected features were included into prediction. In all cases, the achieved accuracy was higher for boys than for girls, which results from the fact that the change of voice with age is larger for men than for women. The achieved results suggest that the presented approach can be employed for accurate age estimation during rapid development in children.

Prediction of menarcheal status of girls using voice features.

A method for evaluating the menarcheal status of girls on the basis of their voice features is presented in the paper. The registration procedure consists of voice recording and measuring 20 anthropological features. The input feature vector is a combination of voice and anthropometric parameters, counting 220 features. The optimal set of parameters was selected using five different methods: Method A - stepwise regression (first forward, then backward regression) performed on features with statistically different means/medians; Method B - stepwise regression (forward and backward) on all features, with age; Method C - stepwise regression as in B; including age, Method D - all features with statistically different means/medians, Method E - all features excluding age. For classification purposes three methods were employed: random forest (RF), support vector machine (SVM) and linear discriminant analysis (LDA) classifier. They were tested with 10-fold cross validation. The classification accuracy for RF using only voice features is higher than using only anthropometric data: 86.86% vs. 81.02% respectively. For the other two classifiers, the results do not show as large a difference: 80.60% vs. 82.80% for SVM and 80.66% vs. 82.34% for LDA. The advantage of voice features is more noticeable with sensitivity: 91.92% vs. 83.06% for RF. The obtained results suggest that the presented method can be used for automatic recognition of girls' menarcheal status using voice signal.

Dynamic time warping in phoneme modeling for fast pronunciation error detection.

The presented paper describes a novel approach to the detection of pronunciation errors. It makes use of the modeling of well-pronounced and mispronounced phonemes by means of the Dynamic Time Warping (DTW) algorithm. Four approaches that make use of the DTW phoneme modeling were developed to detect pronunciation errors: Variations of the Word Structure (VoWS), Normalized Phoneme Distances Thresholding (NPDT), Furthest Segment Search (FSS) and Normalized Furthest Segment Search (NFSS). The performance evaluation of each module was carried out using a speech database of correctly and incorrectly pronounced words in the Polish language, with up to 10 patterns of every trained word from a set of 12 words having different phonetic structures. The performance of DTW modeling was compared to Hidden Markov Models (HMM) that were used for the same four approaches (VoWS, NPDT, FSS, NFSS). The average error rate (AER) was the lowest for DTW with NPDT (AER=0.287) and scored better than HMM with FSS (AER=0.473), which was the best result for HMM. The DTW modeling was faster than HMM for all four approaches. This technique can be used for computer-assisted pronunciation training systems that can work with a relatively small training speech corpus (less than 20 patterns per word) to support speech therapy at home.