Estimation of Subglottal Pressure, Vocal Fold Collision Pressure, and Intrinsic Laryngeal Muscle Activation From Neck-Surface Vibration Using a Neural Network Framework and a Voice Production Model.

Emiro J Ibarra,Daryush D Mehta,Matías Zañartu,Jesús A Parra,Víctor M Espinoza,Gabriel A Alzamendi,Juan P Cortés,Robert E Hillman

doi:10.3389/fphys.2021.732244

Abstract

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.

Highlights

Laryngeal voice disorders have been estimated to affect approximately 30% of the adult population in the United States at some point in their lives (Bhattacharyya, 2014)
We argue that the extraction of additional physiological measures from ambulatory ACC recordings, such as subglottal pressure, vocal fold collision pressure, and laryngeal muscle activation, would provide critical additional insights into the etiologic and pathophysiological mechanisms that underlie hyperfunctional voice disorders and significantly enhance the capability to identify the detrimental daily patterns of vocal behavior associated with these disorders (Espinoza et al, 2017; Galindo et al, 2017; Hillman et al, 2020)
We propose using a neural network (NN) regression architecture trained from a physiologically relevant muscle-controlled voice synthesizer with a triangular body-cover vocal fold model (Alzamendi et al, 2019, 2021) that takes the aerodynamic features as input and provides subglottal pressure, collision pressure, and laryngeal muscle activation as output

Summary

Introduction

Laryngeal voice disorders have been estimated to affect approximately 30% of the adult population in the United States at some point in their lives (Bhattacharyya, 2014). Numerous features have been extracted from the ambulatory recording of the ACC signal, including phonation duration, sound pressure level (SPL), fundamental frequency (fo) (Ghassemi et al, 2014), vocal vibration-dose measures (Titze et al, 2003; Titze and Hunter, 2015), spectral and cepstral measures (Mehta et al, 2015, 2019), and aerodynamic measures (Llico et al, 2015; Cortés et al, 2018) These measures have been used to differentiate the daily voice use of patients with vocal hyperfunction from matched controls (Ghassemi et al, 2014; Cortés et al, 2018; Van Stan et al, 2021) and to track changes related to surgical and voice therapy treatment of hyperfunctional voice disorders (Van Stan et al, 2017b, 2020). Current classification accuracy using these parameters is in the range of 0.7–0.85

Objectives

Methods

Results

Discussion

Conclusion