Deep Learning-Based Analysis of Glottal Attack and Offset Times in Adductor Laryngeal Dystonia.

OBJECTIVE: Diagnosis of adductor laryngeal dystonia (AdLD) is challenging as it mimics voice features of other voice disorders. This could lead to misdiagnosis (or delayed diagnosis) and ineffective treatments of AdLD. This paper develops automated measurements of glottal attack time (GAT) and glottal offset time (GOT) from high-speed videoendoscopy (HSV) in connected speech as objective measures that can potentially facilitate the diagnosis of this disorder in the future. METHODS: HSV data were recorded from vocally normal adults and patients with AdLD during the reading of the "Rainbow Passage" and six CAPE-V (Consensus Auditory-Perceptual Evaluation of Voice) sentences. A deep learning framework was designed and trained to segment the glottal area and detect the vocal fold edges in the HSV dataset. This automated framework allowed us to automatically measure and quantify the GATs and GOTs for the participants. Accordingly, a comparison was held between the obtained measurements among vocally normal speakers and those with AdLD. RESULTS: The automated framework was successfully developed and able to accurately segment the glottal area/edges. The precise automated measurements of GAT and GOT revealed minor, nonsignificant differences compared to the results of manual analysis-showing a strong correlation between the measures by the automated and manual methods. The results showed significant differences in the GAT values between the vocally normal subjects and AdLD patients, with larger variability in both the GAT and GOT measures in the AdLD group. CONCLUSIONS: The developed automated approach for GAT and GOT measurement can be valuable in clinical practice. These quantitative measurements can be used as meaningful biomarkers of the impaired vocal function in AdLD and help its differential diagnosis in the future.

Laryngeal Imaging Study of Glottal Attack/Offset Time in Adductor Spasmodic Dysphonia during Connected Speech.

Adductor spasmodic dysphonia (AdSD) disrupts laryngeal muscle control during speech and, therefore, affects the onset and offset of phonation. In this study, the goal is to use laryngeal high-speed videoendoscopy (HSV) to measure the glottal attack time (GAT) and glottal offset time (GOT) during connected speech for normophonic (vocally normal) and AdSD voices. A monochrome HSV system was used to record readings of six CAPE-V sentences and part of the "Rainbow Passage" from the participants. Three raters visually analyzed the HSV data using a playback software to measure the GAT and GOT. The results show that the GAT was greater in the AdSD group than in the normophonic group; however, the clinical significance of the amount of this difference needs to be studied further. More variability was observed in both GATs and GOTs of the disorder group. Additionally, the GAT and GOT time series were found to be nonstationary for the AdSD group while they were stationary for the normophonic voices. This study shows that the GAT and GOT measures can be potentially used as objective markers to characterize AdSD. The findings will potentially help in the development of standardized measures for voice evaluation and the accurate diagnosis of AdSD.

The Effect of Stimuli Level on Distortion Product Otoacoustic Emission in Normal Hearing Adults.

The goal of this study is to compare three of the most commonly used primary-level relation paradigms (i.e., Scissors, Boys Town 'Optimal', and Equal-Level) in generation of distortion product otoacoustic emissions (DPOAEs) in normal hearing adults. The generator and reflection components were extracted from DPOAEs in each paradigm. The generator and reflection component levels and input/output (I/O) functions were compared across paradigms and primary-tone levels. The results showed a different I/O function growth behavior across frequency and levels among paradigms. The Optimal paradigm showed a systematic change in the generator and reflection component levels and I/O slopes across primary levels among subjects. Moreover, the levels and slopes in the Optimal paradigm were more distinct across levels with less variations across frequency leading to a systematic change in the DPOAE fine structure across levels. The I/O functions were found to be more sensitive to the selected paradigm; especially the I/O function for the reflection component. The I/O functions of the reflection components showed large variability across frequencies due to different frequency shifts in their microstructure depending on the paradigm. The findings of this study suggested the Optimal paradigm as the proper primary-level relation to study cochlear amplification/compression. The findings of this study shows that care needs to be taken in comparing the findings of different studies that generated DPOAEs with a different level-relation paradigm.

Spatial Segmentation for Laryngeal High-Speed Videoendoscopy in Connected Speech.

OBJECTIVE: This study proposes a new computational framework for automated spatial segmentation of the vocal fold edges in high-speed videoendoscopy (HSV) data during connected speech. This spatio-temporal analytic representation of the vocal folds enables the HSV-based measurement of the glottal area waveform and other vibratory characteristics in the context of running speech. METHODS: HSV data were obtained from a vocally normal adult during production of the "Rainbow Passage." An algorithm based on an active contour modeling approach was developed for the analysis of HSV data. The algorithm was applied on a series of HSV kymograms at different intersections of the vocal folds to detect the edges of the vibrating vocal folds across the frames. This edge detection method follows a set of deformation rules for the active contours to capture the edges of the vocal folds through an energy optimization procedure. The detected edges in the kymograms were then registered back to the HSV frames. Subsequently, the glottal area waveform was calculated based on the area of the glottis enclosed by the vocal fold edges in each frame. RESULTS: The developed algorithm successfully captured the edges of the vocal folds in the HSV kymograms. This method led to an automated measurement of the glottal area waveform from the HSV frames during vocalizations in connected speech. CONCLUSION: The proposed algorithm serves as an automated method for spatial segmentation of the vocal folds in HSV data in connected speech. This study is one of the initial steps toward developing HSV-based measures to study vocal fold vibratory characteristics and voice production mechanisms in norm and disorder in the context of connected speech.

Deep-Learning-Based Representation of Vocal Fold Dynamics in Adductor Spasmodic Dysphonia during Connected Speech in High-Speed Videoendoscopy.

OBJECTIVE: Adductor spasmodic dysphonia (AdSD) is a neurogenic dystonia, which causes spasms of the laryngeal muscles. This disorder mainly affects production of connected speech. To understand how AdSD affects vocal fold (VF) movements and hence, the speech signal, it is necessary to study VF kinematics during the running speech. This paper introduces an automated method for analysis of VF vibrations in AdSD using laryngeal high-speed videoendoscopy (HSV) in running speech. METHODS: A monochrome HSV system was used to obtain video recordings from vocally normal individuals and AdSD patients during production of the six CAPE-V sentences and the "Rainbow Passage." A deep neural network was designed based on the UNet architecture. The network was developed for glottal area segmentation in HSV data providing a tool for quantitative analysis of VF vibrations in both norm and AdSD. The network was trained and validated using the manually labeled HSV frames. After training the network, the segmentation quality was quantitatively evaluated against visual analysis results of a test dataset including segregated HSV frames and a short sequence of VF vibrations in consecutive frames. RESULTS: The developed convolutional network was successfully trained and demonstrated an accurate segmentation on the testing dataset with a mean Intersection over Union (IoU) of 0.81 and a mean Boundary-F1 score of 0.93. Moreover, the visual assessment of the automated technique showed an accurate detection of the glottal edges/area in the HSV data even with challenging image quality and excessive laryngeal maneuvers of AdSD patients during the running speech. CONCLUSION: The introduced automated approach provides an accurate representation of the glottal edges/area during connected speech in HSV data for norm and AdSD patients. This method facilitates the development of HSV-based measures to quantify VF dynamics in AdSD. Using HSV to automatically analyze VF vibrations in AdSD can allow for understanding AdSD vocal mechanisms and characteristics.

A Deep Learning Approach for Quantifying Vocal Fold Dynamics During Connected Speech Using Laryngeal High-Speed Videoendoscopy.

PURPOSE: Voice disorders are best assessed by examining vocal fold dynamics in connected speech. This can be achieved using flexible laryngeal high-speed videoendoscopy (HSV), which enables us to study vocal fold mechanics with high temporal details. Analysis of vocal fold vibration using HSV requires accurate segmentation of the vocal fold edges. This article presents an automated deep-learning scheme to segment the glottal area in HSV from which the glottal edges are derived during connected speech. METHOD: Using a custom-built HSV system, data were obtained from a vocally healthy participant reciting the "Rainbow Passage." A deep neural network was designed for glottal area segmentation in the HSV data. A recently introduced hybrid approach by the authors was utilized as an automated labeling tool to train the network on a set of HSV frames, where the glottis region was automatically annotated during vocal fold vibrations. The network was then tested against manually segmented frames using different metrics, intersection over union (IoU), and Boundary F1 (BF) score, and its performance was assessed on various phonatory events on the HSV sequence. RESULTS: The designed network was successfully trained using the hybrid approach, without the need for manual labeling, and tested on the manually labeled data. The performance metrics showed a mean IoU of 0.82 and a mean BF score of 0.96. In addition, the evaluation assessment of the network's performance demonstrated an accurate segmentation of the glottal edges/area even during complex nonstationary phonatory events and when vocal folds were not vibrating, thus overcoming the limitations of the previous hybrid approach that could only be applied to the vibrating vocal folds. CONCLUSIONS: The introduced automated scheme guarantees accurate glottis representation in challenging color HSV data with lower image quality and excessive laryngeal maneuvers during all instances of connected speech. This facilitates the future development of HSV-based measures to assess the running vibratory characteristics of the vocal folds in speakers with and without voice disorder. SUPPLEMENTAL MATERIAL: https://doi.org/10.23641/asha.19798864.

Detection of Vocal Fold Image Obstructions in High-Speed Videoendoscopy During Connected Speech in Adductor Spasmodic Dysphonia: A Convolutional Neural Networks Approach.

OBJECTIVE: Adductor spasmodic dysphonia (AdSD) is a neurogenic voice disorder, affecting the intrinsic laryngeal muscle control. AdSD leads to involuntary laryngeal spasms and only reveals during connected speech. Laryngeal high-speed videoendoscopy (HSV) coupled with a flexible fiberoptic endoscope provides a unique opportunity to study voice production and visualize the vocal fold vibrations in AdSD during speech. The goal of this study is to automatically detect instances during which the image of the vocal folds is optically obstructed in HSV recordings obtained during connected speech. METHODS: HSV data were recorded from vocally normal adults and patients with AdSD during reading of the "Rainbow Passage", six CAPE-V sentences, and production of the vowel /i/. A convolutional neural network was developed and trained as a classifier to detect obstructed/unobstructed vocal folds in HSV frames. Manually labelled data were used for training, validating, and testing of the network. Moreover, a comprehensive robustness evaluation was conducted to compare the performance of the developed classifier and visual analysis of HSV data. RESULTS: The developed convolutional neural network was able to automatically detect the vocal fold obstructions in HSV data in vocally normal participants and AdSD patients. The trained network was tested successfully and showed an overall classification accuracy of 94.18% on the testing dataset. The robustness evaluation showed an average overall accuracy of 94.81% on a massive number of HSV frames demonstrating the high robustness of the introduced technique while keeping a high level of accuracy. CONCLUSIONS: The proposed approach can be used for efficient analysis of HSV data to study laryngeal maneuvers in patients with AdSD during connected speech. Additionally, this method will facilitate development of vocal fold vibratory measures for HSV frames with an unobstructed view of the vocal folds. Indicating parts of connected speech that provide an unobstructed view of the vocal folds can be used for developing optimal passages for precise HSV examination during connected speech and subject-specific clinical voice assessment protocols.

A GENERAL RETURN-MAPPING FRAMEWORK FOR FRACTIONAL VISCO-ELASTO-PLASTICITY.

We develop a fractional return-mapping framework for power-law visco-elasto-plasticity. In our approach, the fractional viscoelasticity is accounted through canonical combinations of Scott-Blair elements to construct a series of well-known fractional linear viscoelastic models, such as Kelvin-Voigt, Maxwell, Kelvin-Zener and Poynting-Thomson. We also consider a fractional quasi-linear version of Fung's model to account for stress/strain nonlinearity. The fractional viscoelastic models are combined with a fractional visco-plastic device, coupled with fractional viscoelastic models involving serial combinations of Scott-Blair elements. We then develop a general return-mapping procedure, which is fully implicit for linear viscoelastic models, and semi-implicit for the quasi-linear case. We find that, in the correction phase, the discrete stress projection and plastic slip have the same form for all the considered models, although with different property and time-step dependent projection terms. A series of numerical experiments is carried out with analytical and reference solutions to demonstrate the convergence and computational cost of the proposed framework, which is shown to be at least first-order accurate for general loading conditions. Our numerical results demonstrate that the developed framework is more flexible, preserves the numerical accuracy of existing approaches while being more computationally tractable in the visco-plastic range due to a reduction of 50% in CPU time. Our formulation is especially suited for emerging applications of fractional calculus in bio-tissues that present the hallmark of multiple viscoelastic power-laws coupled with visco-plasticity.

A Hybrid Machine-Learning-Based Method for Analytic Representation of the Vocal Fold Edges during Connected Speech.

Investigating the phonatory processes in connected speech from high-speed videoendoscopy (HSV) demands the accurate detection of the vocal fold edges during vibration. The present paper proposes a new spatio-temporal technique to automatically segment vocal fold edges in HSV data during running speech. The HSV data were recorded from a vocally normal adult during a reading of the "Rainbow Passage." The introduced technique was based on an unsupervised machine-learning (ML) approach combined with an active contour modeling (ACM) technique (also known as a hybrid approach). The hybrid method was implemented to capture the edges of vocal folds on different HSV kymograms, extracted at various cross-sections of vocal folds during vibration. The k-means clustering method, an ML approach, was first applied to cluster the kymograms to identify the clustered glottal area and consequently provided an initialized contour for the ACM. The ACM algorithm was then used to precisely detect the glottal edges of the vibrating vocal folds. The developed algorithm was able to accurately track the vocal fold edges across frames with low computational cost and high robustness against image noise. This algorithm offers a fully automated tool for analyzing the vibratory features of vocal folds in connected speech.

Anomalous Nonlinear Dynamics Behavior of Fractional Viscoelastic Beams.

Fractional models and their parameters are sensitive to intrinsic microstructural changes in anomalous materials. We investigate how such physics-informed models propagate the evolving anomalous rheology to the nonlinear dynamics of mechanical systems. In particular, we study the vibration of a fractional, geometrically nonlinear viscoelastic cantilever beam, under base excitation and free vibration, where the viscoelasticity is described by a distributed-order fractional model. We employ Hamilton's principle to obtain the equation of motion with the choice of specific material distribution functions that recover a fractional Kelvin-Voigt viscoelastic model of order α. Through spectral decomposition in space, the resulting time-fractional partial differential equation reduces to a nonlinear time-fractional ordinary differential equation, where the linear counterpart is numerically integrated through a direct L1-difference scheme. We further develop a semi-analytical scheme to solve the nonlinear system through a method of multiple scales, yielding a cubic algebraic equation in terms of the frequency. Our numerical results suggest a set of α-dependent anomalous dynamic qualities, such as far-from-equilibrium power-law decay rates, amplitude super-sensitivity at free vibration, and bifurcation in steady-state amplitude at primary resonance.

Temporal Segmentation for Laryngeal High-Speed Videoendoscopy in Connected Speech.

OBJECTIVE: This study proposes a gradient-based method for temporal segmentation of laryngeal high-speed videoendoscopy (HSV) data obtained during connected speech. METHODS: A custom-developed HSV system coupled with a flexible fiberoptic nasolaryngoscope was used to record one vocally normal female participant during reading of the "Rainbow Passage." A gradient-based algorithm was developed to generate a motion window. When applied to the HSV data, the motion window acted as a filter tracking the location of the vibrating vocal folds. The glottal area waveform was estimated using a statistical-based image-processing approach. The vocal fold vibratory frequency was computed by an autocorrelation-based extraction of the fundamental frequency (f0) from the glottal area waveform. Temporal segmentation was then performed based on the f0 contour and automatic detection of the epiglottic obstructions. Additionally, visual temporal segmentation was performed by viewing the HSV images frame by frame to determine the time points of the vocalization onsets and offsets, and the epiglottic obstructions of the glottis. RESULTS: The time points resulting from the automatic and visual temporal segmentation methods were cross-validated. The f0-contour patterns of rise and fall resulting from the automatic algorithm were found to be in agreement with the visual inspection of the vibratory frequency change in the HSV data. CONCLUSIONS: This study demonstrated the feasibility of automatic temporal segmentation of HSV imaging of connected speech, which allows for mapping the video content into onsets, offsets, and epiglottic obstructions for each vocalization. Automated analysis of HSV imaging of connected speech has significant clinical potential for advancing instrumental voice assessment protocols.

Estimation of Round-Trip Outer-Middle Ear Gain Using DPOAEs.

The reported research introduces a noninvasive approach to estimate round-trip outer-middle ear pressure gain using distortion product otoacoustic emissions (DPOAEs). Our ability to hear depends primarily on sound waves traveling through the outer and middle ear toward the inner ear. The role of the outer and middle ear in sound transmission is particularly important for otoacoustic emissions (OAEs), which are sound signals generated in a healthy cochlea and recorded by a sensitive microphone placed in the ear canal. OAEs are used to evaluate the health and function of the cochlea; however, they are also affected by outer and middle ear characteristics. To better assess cochlear health using OAEs, it is critical to quantify the effect of the outer and middle ear on sound transmission. DPOAEs were obtained in two conditions: (i) two-tone and (ii) three-tone. In the two-tone condition, DPOAEs were generated by presenting two primary tones in the ear canal. In the three-tone condition, DPOAEs at the same frequencies (as in the two-tone condition) were generated by the interaction of the lower frequency primary tone in the two-tone condition with a distortion product generated by the interaction of two other external tones. Considering how the primary tones and DPOAEs of the aforementioned conditions were affected by the forward and reverse outer-middle ear transmission, an estimate of the round-trip outer-middle ear pressure gain was obtained. The round-trip outer-middle ear gain estimates ranged from -39 to -17 dB between 1 and 3.3 kHz.

Asymmetric inhibitory treatment effects in multilingual aphasia.

Findings from recent psycholinguistic studies of bilingual processing support the hypothesis that both languages of a bilingual are always active and that bilinguals continually engage in processes of language selection. This view aligns with the convergence hypothesis of bilingual language representation. Furthermore, it is hypothesized that when bilinguals perform a task in one language they need to inhibit their other, nontarget language(s) and that stronger inhibition is required when the task is performed in the weaker language than in the stronger one. The study of multilingual individuals who acquire aphasia resulting from a focal brain lesion offers a unique opportunity to test the convergence hypothesis and the inhibition asymmetry. We report on a trilingual person with chronic nonfluent aphasia who at the time of testing demonstrated greater impairment in her first acquired language (Persian) than in her third, later learned language (English). She received treatment in English followed by treatment in Persian. An examination of her connected language production revealed improvement in her grammatical skills in each language following intervention in that language, but decreased grammatical accuracy in English following treatment in Persian. The increased error rate was evident in structures that are used differently in the two languages (e.g., auxiliary verbs). The results support the prediction that greater inhibition is applied to the stronger language than to the weaker language, regardless of their age of acquisition. We interpret the findings as consistent with convergence theories that posit overlapping neuronal representation and simultaneous activation of multiple languages and with proficiency-dependent asymmetric inhibition in multilinguals.