RESUMO
Many voice disorders are linked to imbalanced muscle activity and known to exhibit asymmetric vocal fold vibration. However, the relation between imbalanced muscle activation and asymmetric vocal fold vibration is not well understood. This study introduces an asymmetric triangular body-cover model of the vocal folds, controlled by the activation of bilateral intrinsic laryngeal muscles, to investigate the effects of muscle imbalance on vocal fold oscillation. Various scenarios were considered, encompassing imbalance in individual muscles and muscle pairs, as well as accounting for asymmetry in lumped element parameters. Measurements of amplitude and phase asymmetries were employed to match the oscillatory behavior of two pathological cases: unilateral paralysis and muscle tension dysphonia. The resulting simulations exhibit muscle imbalance consistent with expectations in the composition of these voice disorders, yielding asymmetries exceeding 30% for paralysis and below 5% for dysphonia. This underscores the relevance of muscle imbalance in representing phonatory scenarios and its potential for characterizing asymmetry in vocal fold vibration.
Assuntos
Músculos Laríngeos , Fonação , Vibração , Prega Vocal , Prega Vocal/fisiologia , Prega Vocal/fisiopatologia , Humanos , Músculos Laríngeos/fisiologia , Músculos Laríngeos/fisiopatologia , Simulação por Computador , Disfonia/fisiopatologia , Paralisia das Pregas Vocais/fisiopatologia , Modelos Biológicos , Fenômenos BiomecânicosRESUMO
Mathematical models that accurately simulate the physiological systems of the human body serve as cornerstone instruments for advancing medical science and facilitating innovative clinical interventions. One application is the modeling of the subglottal tract and neck skin properties for its use in the ambulatory assessment of vocal function, by enabling non-invasive monitoring of glottal airflow via a neck surface accelerometer. For the technique to be effective, the development of an accurate building block model for the subglottal tract is required. Such a model is expected to utilize glottal volume velocity as the input parameter and yield neck skin acceleration as the corresponding output. In contrast to preceding efforts that employed frequency-domain methods, the present paper leverages system identification techniques to derive a parsimonious continuous-time model of the subglottal tract using time-domain data samples. Additionally, an examination of the model order is conducted through the application of various information criteria. Once a low-order model is successfully fitted, an inverse filter based on a Kalman smoother is utilized for the estimation of glottal volume velocity and related aerodynamic metrics, thereby constituting the most efficient execution of these estimates thus far. Anticipated reductions in computational time and complexity due to the lower order of the subglottal model hold particular relevance for real-time monitoring. Simultaneously, the methodology proves efficient in generating a spectrum of aerodynamic features essential for ambulatory vocal function assessment.
RESUMO
Many voice disorders are linked to imbalanced muscle activity and known to exhibit asymmetric vocal fold vibration. However, the relation between imbalanced muscle activation and asymmetric vocal fold vibration is not well understood. This study introduces an asymmetric triangular body-cover model of the vocal folds, controlled by the activation of intrinsic laryngeal muscles, to investigate the effects of muscle imbalance on vocal fold oscillation. Various scenarios were considered, encompassing imbalance in individual muscles and muscle pairs, as well as accounting for asymmetry in lumped element parameters. The results highlight the antagonistic effect between the thyroarytenoid and cricothyroid muscles on the elastic and mass components of the vocal folds, as well as the impact on the vocal process from the imbalance in the lateral cricoarytenoid and interarytenoid adductor muscles. Measurements of amplitude and phase asymmetry were employed to emulate the oscillatory behavior of two pathological cases: unilateral paralysis and muscle tension dysphonia. The resulting simulations exhibit muscle imbalance consistent with expectations in the composition of these voice disorders, yielding asymmetries exceeding 30% for paralysis and below 5% for dysphonia. This underscores the versatility of muscle imbalance in representing phonatory scenarios and its potential for characterizing asymmetry in vocal fold vibration.
RESUMO
The use of non-invasive skin accelerometers placed over the extrathoracic trachea has been proposed in the literature for measuring vocal function. Glottal airflow is estimated using inverse filtering or Bayesian techniques based on a subglottal impedance-based model when utilizing these sensors. However, deviations in glottal airflow estimates can arise due to sensor positioning and model mismatch, and addressing them requires a significant computational load. In this paper, we utilize system identification techniques to obtain a low order state-space representation of the subglottal impedance-based model. We then employ the resulting low order model in a Kalman smoother to estimate the glottal airflow. Our proposed approach reduces the model order by 94% and requires only 1.5% of the computing time compared to previous Bayesian methods in the literature, while achieving slightly better accuracy when correcting for glottal airflow deviations. Additionally, our Kalman smoother approach provides a measure of uncertainty in the airflow estimate, which is valuable when measurements are taken under different conditions. With its comparable accuracy in signal estimation and reduced computational load, the proposed approach has the potential for real-time estimation of glottal airflow and its associated uncertainty in wearable voice ambulatory monitors using neck-surface acceleration.
RESUMO
End-to-end deep learning models have shown promising results for the automatic screening of Parkinson's disease by voice and speech. However, these models often suffer degradation in their performance when applied to scenarios involving multiple corpora. In addition, they also show corpus-dependent clusterings. These facts indicate a lack of generalisation or the presence of certain shortcuts in the decision, and also suggest the need for developing new corpus-independent models. In this respect, this work explores the use of domain adversarial training as a viable strategy to develop models that retain their discriminative capacity to detect Parkinson's disease across diverse datasets. The paper presents three deep learning architectures and their domain adversarial counterparts. The models were evaluated with sustained vowels and diadochokinetic recordings extracted from four corpora with different demographics, dialects or languages, and recording conditions. The results showed that the space distribution of the embedding features extracted by the domain adversarial networks exhibits a higher intra-class cohesion. This behaviour is supported by a decrease in the variability and inter-domain divergence computed within each class. The findings suggest that domain adversarial networks are able to learn the common characteristics present in Parkinsonian voice and speech, which are supposed to be corpus, and consequently, language independent. Overall, this effort provides evidence that domain adaptation techniques refine the existing end-to-end deep learning approaches for Parkinson's disease detection from voice and speech, achieving more generalizable models.
RESUMO
Incomplete glottal closure is a laryngeal configuration wherein the glottis is not fully obstructed prior to phonation. It has been linked to inefficient voice production and voice disorders. Various incomplete glottal closure patterns can arise and the mechanisms driving them are not well understood. In this work, we introduce an Euler-Bernoulli composite beam vocal fold (VF) model that produces qualitatively similar incomplete glottal closure patterns as those observed in experimental and high-fidelity numerical studies, thus offering insights into the potential underlying physical mechanisms. Refined physiological insights are pursued by incorporating the beam model into a VF posturing model that embeds the five intrinsic laryngeal muscles. Analysis of the combined model shows that co-activating the lateral cricoarytenoid (LCA) and interarytenoid (IA) muscles without activating the thyroarytenoid (TA) muscle results in a bowed (convex) VF geometry with closure at the posterior margin only; this is primarily attributed to the reactive moments at the anterior VF margin. This bowed pattern can also arise during VF compression (due to extrinsic laryngeal muscle activation for example), wherein the internal moment induced passively by the TA muscle tissue is the predominant mechanism. On the other hand, activating the TA muscle without incorporating other adductory muscles results in anterior and mid-membranous glottal closure, a concave VF geometry, and a posterior glottal opening driven by internal moments induced by TA muscle activation. In the case of initial full glottal closure, the posterior cricoarytenoid (PCA) muscle activation cancels the adductory effects of the LCA and IA muscles, resulting in a concave VF geometry and posterior glottal opening. Furthermore, certain maneuvers involving co-activation of all adductory muscles result in an hourglass glottal shape due to a reactive moment at the anterior VF margin and moderate internal moment induced by TA muscle activation. These findings have implications regarding potential laryngeal maneuvers in patients with voice disorders involving imbalances or excessive tension in the laryngeal muscles such as muscle tension dysphonia.
Assuntos
Distúrbios da Voz , Voz , Humanos , Prega Vocal/fisiologia , Glote/fisiologia , Voz/fisiologia , Fonação/fisiologiaRESUMO
Incomplete glottal closure is a laryngeal configuration wherein the glottis is not fully obstructed prior to phonation. In this work, we introduce an Euler-Bernoulli composite beam vocal fold (VF) model that produces qualitatively similar incomplete glottal closure patterns as those observed in experimental and high-fidelity numerical studies, thus offering insights in to the potential underlying physical mechanisms. Refined physiological insights are pursued by incorporating the beam model into a VF posturing model that embeds the five intrinsic laryngeal muscles. Analysis of the combined model shows that co-activating the lateral cricoarytenoid (LCA) and interarytenoid (IA) muscles without activating the thyroarytenoid (TA) muscle results in a bowed (convex) VF geometry with closure at the posterior margin only; this is primarily attributed to the reactive moments at the anterior VF margin. This bowed pattern can also arise during VF compression (due to extrinsic laryngeal muscle activation for example), wherein the internal moment induced passively by the TA muscle tissue is the predominant mechanism. On the other hand, activating the TA muscle without incorporating other adductory muscles results in anterior and mid-membranous glottal closure, a concave VF geometry, and a posterior glottal opening driven by internal moments induced by TA muscle activation. In the case of initial full glottal closure, the posterior cricoarytenoid (PCA) muscle activation cancels the adductory effects of the LCA and IA muscles, resulting in a concave VF geometry and posterior glottal opening. Furthermore, certain maneuvers involving co-activation of all adductory muscles result in an hourglass glottal shape due to a reactive moment at the anterior VF margin and moderate internal moment induced by TA muscle activation.
RESUMO
Swelling in the vocal folds is caused by the local accumulation of fluid, and has been implicated as a phase in the development of phonotraumatic vocal hyperfunction and related structural pathologies, such as vocal fold nodules. It has been posited that small degrees of swelling may be protective, but large amounts may lead to a vicious cycle wherein the engorged folds lead to conditions that promote further swelling, leading to pathologies. As a first effort to explore the mechanics of vocal fold swelling and its potential role in the etiology of voice disorders, this study employs a finite-element model with swelling confined to the superficial lamina propria, which changes the volume, mass, and stiffness of the cover layer. The impacts of swelling on a number of vocal fold kinematic and damage measures, including von Mises stress, internal viscous dissipation, and collision pressure, are presented. Swelling has small but consistent effects on voice outputs, including a reduction in fundamental frequency with increasing swelling (10 Hz at 30 % swelling). Average von Mises stress decreases slightly for small degrees of swelling but increases at large magnitudes, consistent with expectations for a vicious cycle. Both viscous dissipation and collision pressure consistently increase with the magnitude of swelling. This first effort at modeling the impact of swelling on vocal fold kinematics, kinetics, and damage measures highlights the complexity with which phonotrauma can influence performance metrics. Further identification and exploration of salient candidate measures of damage and refined studies coupling swelling with local phonotrauma are expected to shed further light on the etiological pathways of phonotraumatic vocal hyperfunction.
Assuntos
Mucosa , Prega Vocal , Fenômenos Biomecânicos , Cinética , FísicaRESUMO
Neck muscles play important roles in various physiological tasks, including swallowing, head stabilization, and phonation. The mechanisms by which neck muscles influence phonation are not well understood, with conflicting reports on the change in fundamental frequency for ostensibly the same neck muscle activation scenarios. In this work, we introduce a reduced-order muscle-controlled vocal fold model, comprising both intrinsic muscle control and extrinsic muscle effects. The model predicts that when the neck muscles pull the thyroid cartilage in the superior-anterior direction (with a sufficiently large anterior component), inferior direction, or inferior-anterior direction, tension in the vocal folds increases, leading to fundamental frequency rise during sustained phonation. On the other hand, pulling in the superior direction, superior-posterior direction, or inferior-posterior direction (with a sufficiently large posterior component) tends to decrease vocal fold tension and phonation fundamental frequency. Varying the pulling force location alters the posture and phonation biomechanics, depending on the force direction. These findings suggest potential roles of particular neck muscles in modulating phonation fundamental frequency, with implications for vocal hyperfunction.
Assuntos
Músculos Laríngeos , Fonação , Músculos Laríngeos/fisiologia , Fonação/fisiologia , Prega Vocal/fisiologia , Fenômenos Biomecânicos , Estimulação ElétricaRESUMO
Synthetic vocal fold (VF) replicas were used to explore the role of nodule size and stiffness on kinematic, aerodynamic, and acoustic measures of voiced speech production. Emphasis was placed on determining how changes in collision pressure may contribute to the development of phonotrauma. This was performed by adding spherical beads with different sizes and moduli of elasticity at the middle of the medial surface of synthetic silicone VF models, representing nodules of varying size and stiffness. The VF models were incorporated into a hemilaryngeal flow facility. For each case, self-sustained oscillations were investigated at the phonation threshold pressure. It was found that increasing the nodule diameter increased the open quotient, phonation threshold pressure, and phonation threshold flow rate. However, these values did not change considerably as a function of the modulus of elasticity of the nodule. Nevertheless, the ratio of collision pressure to subglottal pressure increased significantly for both increasing nodule size and stiffness. This suggests that over time, both growth in size and fibrosis of nodules will lead to an increasing cycle of compensatory vocal hyperfunction that accelerates phonotrauma.
Assuntos
Vibração , Prega Vocal , Pressão , Fonação , ElasticidadeRESUMO
The neurocomputational model 'Directions into Velocities of Articulators' (DIVA) was developed to account for various aspects of normal and disordered speech production and acquisition. The neural substrates of DIVA were established through functional magnetic resonance imaging (fMRI), providing physiological validation of the model. This study introduces DIVA_EEG an extension of DIVA that utilizes electroencephalography (EEG) to leverage the high temporal resolution and broad availability of EEG over fMRI. For the development of DIVA_EEG, EEG-like signals were derived from original equations describing the activity of the different DIVA maps. Synthetic EEG associated with the utterance of syllables was generated when both unperturbed and perturbed auditory feedback (first formant perturbations) were simulated. The cortical activation maps derived from synthetic EEG closely resembled those of the original DIVA model. To validate DIVA_EEG, the EEG of individuals with typical voices (N = 30) was acquired during an altered auditory feedback paradigm. The resulting empirical brain activity maps significantly overlapped with those predicted by DIVA_EEG. In conjunction with other recent model extensions, DIVA_EEG lays the foundations for constructing a complete neurocomputational framework to tackle vocal and speech disorders, which can guide model-driven personalized interventions.
RESUMO
OBJECTIVES: Relative fundamental frequency (RFF) is an acoustic measure of changes in fundamental frequency during voicing transitions. The physiological mechanisms underlying RFF remain unclear. Recent modeling suggests that changes in RFF during voicing offset are due to decreases in overall system stiffness as a direct result of the cessation of vocal fold collision. To evaluate this finding empirically, here we examined whether variable timing between the end of vocal fold collision and the final voicing cycle used to calculate RFF explained the variability in RFF across individual voicing offset utterances. METHODS: RFF during voicing offset was calculated from /ifi/ utterances produced by 35 participants under endoscopy, with and without vocal effort. RFF was calculated via two methods, in which utterances were aligned by (1) the end of vocal fold collision, or (2) the end of voicing. Analyses of variance were used to determine the effects of vocal effort and RFF method on the mean and standard deviation of RFF. RESULTS: Aligning by vocal fold collision resulted in statistically significantly lower standard deviations. RFF means were statistically higher using the collision method; however, the degree of vocal effort was statistically significant regardless of the method. CONCLUSIONS: These results provide empirical evidence to support that decreases in RFF during voicing offset are a result of decreases in system stiffness due to termination of vocal fold collision.
RESUMO
Subglottal Impedance-Based Inverse Filtering (IBIF) allows for the continuous, non-invasive estimation of glottal airflow from a surface accelerometer placed over the anterior neck skin below the larynx. It has been shown to be advantageous for the ambulatory monitoring of vocal function, specifically in the use of high-order statistics to understand long-term vocal behavior. However, during long-term ambulatory recordings over several days, conditions may drift from the laboratory environment where the IBIF parameters were initially estimated due to sensor positioning, skin attachment, or temperature, among other factors. Observation uncertainties and model mismatch may result in significant deviations in the glottal airflow estimates; unfortunately, they are very difficult to quantify in ambulatory conditions due to a lack of a reference signal. To address this issue, we propose a Kalman filter implementation of the IBIF filter, which allows for both estimating the model uncertainty and adapting the airflow estimates to correct for signal deviations. One-way analysis of variance (ANOVA) results from laboratory experiments using the Rainbow Passage indicate an improvement using the modified Kalman filter on amplitude-based measures for phonotraumatic vocal hyperfunction (PVH) subjects compared to the standard IBIF; the latter showing a statistically difference (p-value = 0.02, F = 4.1) with respect to a reference glottal volume velocity signal estimated from a single notch filter used here as ground-truth in this work. In contrast, maximum flow declination rates from subjects with vocal phonotrauma exhibit a small but statistically difference between the ground-truth signal and the modified Kalman filter when using one-way ANOVA (p-value = 0.04, F = 3.3). Other measures did not have significant differences with either the modified Kalman filter or IBIF compared to ground-truth, with the exception of H1-H2, whose performance deteriorates for both methods. Overall, both methods (modified Kalman filter and IBIF) show similar glottal airflow measures, with the advantage of the modified Kalman filter to improve amplitude estimation. Moreover, Kalman filter deviations from the IBIF output airflow might suggest a better representation of some fine details in the ground-truth glottal airflow signal. Other applications may take more advantage from the adaptation offered by the modified Kalman filter implementation.
RESUMO
PURPOSE: This exploratory study aims to investigate variations in voice production in the presence of background noise (Lombard effect) in individuals with nonphonotraumatic vocal hyperfunction (NPVH) and individuals with typical voices using acoustic, aerodynamic, and vocal fold vibratory measures of phonatory function. METHOD: Nineteen participants with NPVH and 19 participants with typical voices produced simple vocal tasks in three sequential background conditions: baseline (in quiet), Lombard (in noise), and recovery (5 min after removing the noise). The Lombard condition consisted of speech-shaped noise at 80 dB SPL through audiometric headphones. Acoustic measures from a microphone, glottal aerodynamic parameters estimated from the oral airflow measured with a circumferentially vented pneumotachograph mask, and vocal fold vibratory parameters from high-speed videoendoscopy were analyzed. RESULTS: During the Lombard condition, both groups exhibited a decrease in open quotient and increases in sound pressure level, peak-to-peak glottal airflow, maximum flow declination rate, and subglottal pressure. During the recovery condition, the acoustic and aerodynamic measures of individuals with typical voices returned to those of the baseline condition; however, recovery measures for individuals with NPVH did not return to baseline values. CONCLUSIONS: As expected, individuals with NPVH and participants with typical voices exhibited a Lombard effect in the presence of elevated background noise levels. During the recovery condition, individuals with NPVH did not return to their baseline state, pointing to a persistence of the Lombard effect after noise removal. This behavior could be related to disruptions in laryngeal motor control and may play a role in the etiology of NPVH. SUPPLEMENTAL MATERIAL: https://doi.org/10.23641/asha.20415600.
Assuntos
Prega Vocal , Voz , Acústica , Glote , Humanos , FonaçãoRESUMO
PURPOSE: The goal of this study was to experimentally evaluate how compensating for the adverse acoustic effects of a posterior glottal opening (PGO) by increasing subglottal pressure and changing supraglottal compression, as have been associated with vocal hyperfunction, influences the risk of vocal fold (VF) trauma. METHOD: A self-oscillating synthetic silicone model of the VFs with an airflow bypass that modeled a PGO was investigated in a hemilaryngeal flow facility. The influence of compensatory mechanisms on collision pressure and dissipated collision power was investigated for different PGO areas and supraglottal compression. Compensatory behaviors were mimicked by increasing the subglottal pressure to achieve a target sound pressure level (SPL). RESULTS: Increasing the subglottal pressure to compensate for decreased SPL due to a PGO produced higher values for both collision pressure and dissipated collision power. Whereas a 10-mm2 PGO area produced a 12% increase in the peak collision pressure, the dissipated collision power increased by 122%, mainly due to an increase in the magnitude of the collision velocity. This suggests that the value of peak collision pressure may not fully capture the mechanisms by which phonotrauma occurs. It was also found that an optimal value of supraglottal compression exists that maximizes the radiated SPL, indicating the potential utility of supraglottal compression as a compensatory mechanism. CONCLUSIONS: Larger PGO areas are expected to increase the risk of phonotrauma due to the concomitant increase in dissipated collision power associated with maintaining SPL. Furthermore, the risk of VF damage may not be fully characterized by only the peak collision pressure.
Assuntos
Doenças da Laringe , Laringe , Glote , Humanos , Fonação , Silicones , Prega VocalRESUMO
In an effort to mitigate the 2019 novel coronavirus disease pandemic, mask wearing and social distancing have become standard practices. While effective in fighting the spread of the virus, these protective measures have been shown to deteriorate speech perception and sound intensity, which necessitates speaking louder to compensate. The goal of this paper is to investigate via numerical simulations how compensating for mask wearing and social distancing affects measures associated with vocal health. A three-mass body-cover model of the vocal folds (VFs) coupled with the sub- and supraglottal acoustic tracts is modified to incorporate mask and distance dependent acoustic pressure models. The results indicate that sustaining target levels of intelligibility and/or sound intensity while using these protective measures may necessitate increased subglottal pressure, leading to higher VF collision and, thus, potentially inducing a state of vocal hyperfunction, a progenitor to voice pathologies.
Assuntos
COVID-19 , Voz , COVID-19/prevenção & controle , Humanos , Fonação , Vibração , Prega VocalRESUMO
Many voice disorders are the result of intricate neural and/or biomechanical impairments that are poorly understood. The limited knowledge of their etiological and pathophysiological mechanisms hampers effective clinical management. Behavioral studies have been used concurrently with computational models to better understand typical and pathological laryngeal motor control. Thus far, however, a unified computational framework that quantitatively integrates physiologically relevant models of phonation with the neural control of speech has not been developed. Here, we introduce LaDIVA, a novel neurocomputational model with physiologically based laryngeal motor control. We combined the DIVA model (an established neural network model of speech motor control) with the extended body-cover model (a physics-based vocal fold model). The resulting integrated model, LaDIVA, was validated by comparing its model simulations with behavioral responses to perturbations of auditory vocal fundamental frequency (fo) feedback in adults with typical speech. LaDIVA demonstrated capability to simulate different modes of laryngeal motor control, ranging from short-term (i.e., reflexive) and long-term (i.e., adaptive) auditory feedback paradigms, to generating prosodic contours in speech. Simulations showed that LaDIVA's laryngeal motor control displays properties of motor equivalence, i.e., LaDIVA could robustly generate compensatory responses to reflexive vocal fo perturbations with varying initial laryngeal muscle activation levels leading to the same output. The model can also generate prosodic contours for studying laryngeal motor control in running speech. LaDIVA can expand the understanding of the physiology of human phonation to enable, for the first time, the investigation of causal effects of neural motor control in the fine structure of the vocal signal.
Assuntos
Percepção da Fala , Voz , Adulto , Retroalimentação Sensorial , Humanos , Músculos Laríngeos/fisiologia , Fala/fisiologia , Percepção da Fala/fisiologia , Voz/fisiologiaRESUMO
Poor laryngeal muscle coordination that results in abnormal glottal posturing is believed to be a primary etiologic factor in common voice disorders such as non-phonotraumatic vocal hyperfunction. Abnormal activity of antagonistic laryngeal muscles is hypothesized to play a key role in the alteration of normal vocal fold biomechanics that results in the dysphonia associated with such disorders. Current low-order models of the vocal folds are unsatisfactory to test this hypothesis since they do not capture the co-contraction of antagonist laryngeal muscle pairs. To address this limitation, a self-sustained triangular body-cover model with full intrinsic muscle control is introduced. The proposed scheme shows good agreement with prior studies using finite element models, excised larynges, and clinical studies in sustained and time-varying vocal gestures. Simulations of vocal fold posturing obtained with distinct antagonistic muscle activation yield clear differences in kinematic, aerodynamic, and acoustic measures. The proposed tool is deemed sufficiently accurate and flexible for future comprehensive investigations of non-phonotraumatic vocal hyperfunction and other laryngeal motor control disorders.
Assuntos
Disfonia , Voz , Glote , Humanos , Músculos Laríngeos/fisiologia , Prega Vocal/fisiologia , Voz/fisiologiaRESUMO
The aerodynamic voice assessment of subglottal air pressure can discriminate between speakers with typical voices from patients with voice disorders, with further evidence validating subglottal pressure as a clinical outcome measure. Although estimating subglottal pressure during phonation is an important component of a standard voice assessment, current methods for estimating subglottal pressure rely on non-natural speech tasks in a clinical or laboratory setting. This study reports on the validation of a method for subglottal pressure estimation in individuals with and without voice disorders that can be translated to connected speech to enable the monitoring of vocal function and behavior in real-world settings. During a laboratory calibration session, a participant-specific multiple regression model was derived to estimate subglottal pressure from a neck-surface vibration signal that can be recorded during natural speech production. The model was derived for vocally typical individuals and patients diagnosed with phonotraumatic vocal fold lesions, primary muscle tension dysphonia, and unilateral vocal fold paralysis. Estimates of subglottal pressure using the developed method exhibited significantly lower error than alternative methods in the literature, with average errors ranging from 1.13 to 2.08 cm H2O for the participant groups. The model was then applied during activities of daily living, thus yielding ambulatory estimates of subglottal pressure for the first time in these populations. Results point to the feasibility and potential of real-time monitoring of subglottal pressure during an individual's daily life for the prevention, assessment, and treatment of voice disorders.
RESUMO
The ambulatory assessment of vocal function can be significantly enhanced by having access to physiologically based features that describe underlying pathophysiological mechanisms in individuals with voice disorders. This type of enhancement can improve methods for the prevention, diagnosis, and treatment of behaviorally based voice disorders. Unfortunately, the direct measurement of important vocal features such as subglottal pressure, vocal fold collision pressure, and laryngeal muscle activation is impractical in laboratory and ambulatory settings. In this study, we introduce a method to estimate these features during phonation from a neck-surface vibration signal through a framework that integrates a physiologically relevant model of voice production and machine learning tools. The signal from a neck-surface accelerometer is first processed using subglottal impedance-based inverse filtering to yield an estimate of the unsteady glottal airflow. Seven aerodynamic and acoustic features are extracted from the neck surface accelerometer and an optional microphone signal. A neural network architecture is selected to provide a mapping between the seven input features and subglottal pressure, vocal fold collision pressure, and cricothyroid and thyroarytenoid muscle activation. This non-linear mapping is trained solely with 13,000 Monte Carlo simulations of a voice production model that utilizes a symmetric triangular body-cover model of the vocal folds. The performance of the method was compared against laboratory data from synchronous recordings of oral airflow, intraoral pressure, microphone, and neck-surface vibration in 79 vocally healthy female participants uttering consecutive /pæ/ syllable strings at comfortable, loud, and soft levels. The mean absolute error and root-mean-square error for estimating the mean subglottal pressure were 191 Pa (1.95 cm H2O) and 243 Pa (2.48 cm H2O), respectively, which are comparable with previous studies but with the key advantage of not requiring subject-specific training and yielding more output measures. The validation of vocal fold collision pressure and laryngeal muscle activation was performed with synthetic values as reference. These initial results provide valuable insight for further vocal fold model refinement and constitute a proof of concept that the proposed machine learning method is a feasible option for providing physiologically relevant measures for laboratory and ambulatory assessment of vocal function.