Speech and Hearing Science Commons^™

Toward Generalizable Machine Learning Models In Speech, Language, And Hearing Sciences: Estimating Sample Size And Reducing Overfitting, Hamzeh Ghasemzadeh, Robert E Hillman, Daryush D Mehta

Student and Faculty Publications

PURPOSE: Many studies using machine learning (ML) in speech, language, and hearing sciences rely upon cross-validations with single data splitting. This study's first purpose is to provide quantitative evidence that would incentivize researchers to instead use the more robust data splitting method of nested

METHOD: First, the significant impact of different cross-validations on ML outcomes was demonstrated using real-world clinical data. Then, Monte Carlo simulations were used to quantify the interactions among the employed cross-validation method, the discriminative power of features, the dimensionality of the feature space, the dimensionality of the model, and the sample size. Four different cross-validation methods …

Quantifying The Occupational Voice Use Of Teachers, Sarah E Eastman, Hamzeh Ghasemzadeh, Jarrad Van Stan, Robert E Hillman, Daryush D Mehta

Student and Faculty Publications

PURPOSE: The teaching profession is a high-voice use occupation at elevated risk for developing voice disorders. Continued research on teachers' vocal demands is necessary to advocate for and establish vocal health programs. This study quantified ambulatory vocal dose measures for teachers during both on- and off-work periods, comparing their occupational voice use to that in other studies that have reported percent phonation ranging from 17% to 30%.

METHOD: Participants included 26 full-time, female school teachers between 23 and 55 years of age across multiple grades and subjects, including individuals with and without a voice disorder. Ambulatory voice data were collected …

Acoustic Voice And Speech Biomarkers Of Treatment Status During Hospitalization For Acute Decompensated Heart Failure, Olivia M Murton, G William Dec, Robert E Hillman, Maulik D Majmudar, Johannes Steiner, John V Guttag, Daryush D Mehta

Student and Faculty Publications

This study investigates acoustic voice and speech features as biomarkers for acute decompensated heart failure (ADHF), a serious escalation of heart failure symptoms including breathlessness and fatigue. ADHF-related systemic fluid accumulation in the lungs and laryngeal tissues is hypothesized to affect phonation and respiration for speech. A set of daily spoken recordings from 52 patients undergoing inpatient ADHF treatment was analyzed to identify voice and speech biomarkers for ADHF and to examine the trajectory of biomarkers during treatment. Results indicated that speakers produce more stable phonation, a more creaky voice, faster speech rates, and longer phrases after ADHF treatment compared …

Effect Of Nodule Size And Stiffness On Phonation Threshold And Collision Pressures In A Synthetic Hemilaryngeal Vocal Fold Model, Mohsen Motie-Shirazi, Matías Zañartu, Sean D Peterson, Daryush D Mehta, Robert E Hillman, Byron D Erath

Student and Faculty Publications

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 …

Association Of Hearing Loss And Tinnitus Symptoms With Health-Related Quality Of Life Among Long-Term Oropharyngeal Cancer Survivors, Puja Aggarwal, Marc-Elie Nader, Paul W Gidley, Raj Pratihar, Shirin Jivani, Adam S Garden, Frank E Mott, Ryan P Goepfert, Christopher Wallace Ogboe, Camille Charles, Clifton D Fuller, Stephen Y Lai, G Brandon Gunn, Erich M Sturgis, Ehab Y Hanna, Katherine A Hutcheson, Sanjay Shete

Student and Faculty Publications

BACKGROUND: This study investigated the association of hearing loss and tinnitus with overall health-related quality of life (HRQoL) among long-term oropharyngeal cancer (OPC) survivors.

METHODS: This study included OPC survivors treated between 2000 and 2013 and surveyed from September 2015 to July 2016. Hearing loss and tinnitus were measured by asking survivors to rate their "difficulty with hearing loss and/or ringing in the ears" from 0 (not present) to 10 (as bad as you can imagine). Hearing loss and tinnitus scores were categorized as follows: 0 for none, 1-4 for mild, and 5-10 for moderate to severe. The primary outcome …

Aphasia In Multilingual Patients, Mira Goral, Zahra Hejazi

Publications and Research

Purpose of Review

We summarize recent published work concerning assessment and treatment of aphasia in bilingual and multilingual people and review current related models of treatment outcomes. As well, we discuss studies that address the recently debated topic of cognitive processes in bilingual individuals with aphasia, with a focus on the effects of bilingualism on aphasia recovery and its potential protective effects.

Recent Findings

Providing assessment and treatment tools that best serve multilingual individuals with aphasia and unpacking the variables and mechanisms that underlie response to treatment have emerged as goals of several recent studies. Additionally, while findings are still …

Diagnosing And Managing Post-Stroke Aphasia, Shannon M. Sheppard, Rajani Sebastian

Communication Sciences and Disorders Faculty Articles and Research

Introduction: Aphasia is a debilitating language disorder and even mild forms of aphasia can negatively affect functional outcomes, mood, quality of life, social participation, and the ability to return to work. Language deficits after post-stroke aphasia are heterogeneous.

Areas covered: The first part of this manuscript reviews the traditional syndrome-based classification approach as well as recent advances in aphasia classification that incorporate automatic speech recognition for aphasia classification. The second part of this manuscript reviews the behavioral approaches to aphasia treatment and recent advances such as noninvasive brain stimulation techniques and pharmacotherapy options to augment the effectiveness of …

Hypothesis Of K+-Recycling Defect Is Not A Primary Deafness Mechanism For Cx26 (Gjb2) Deficiency, Hong-Bo Zhao

Otolaryngology--Head & Neck Surgery Faculty Publications

K⁺-recycling defect is a long-standing hypothesis for deafness mechanism of Connexin26 (Cx26, GJB2) mutations, which cause the most common hereditary deafness and are responsible for >50% of nonsyndromic hearing loss. The hypothesis states that Cx26 deficiency may disrupt inner ear gap junctions and compromise sinking and recycling of expelled K⁺ ions after hair cell excitation, causing accumulation of K⁺-ions in the extracellular space around hair cells producing K⁺-toxicity, which eventually induces hair cell degeneration and hearing loss. However, this hypothesis has never been directly evidenced, even though it has been widely referred …

Pedigree Structure And Kinship Measurements Of A Mid-Michigan Community: A New North American Population Isolate Identified, Joseph D. Bonner, Rachel Fisher, James Klein, Qing Lu, Ellen Wilch, Karen H. Friderici, Jill L. Elfenbein, Debra L. Schutte, Brian C. Schutte

Human Biology Open Access Pre-Prints

Previous studies identified a cluster of individuals with an autosomal recessive form of deafness that resides in a small region of mid-Michigan. We hypothesized that affected members from this community descend from a defined founder population. Using public records and personal interviews, we constructed a genealogical database that includes the affected individuals and their extended families as descendants of 461 settlers who emigrated from the Eifel region of Germany between 1836 and 1875. The genealogical database represents a 13-generation pedigree that includes 27,747 descendants of these settlers. Among these descendants, 13,784 are presumed living. Many of the extant descendants reside …

Genetics Of Peripheral Vestibular Dysfunction: Lessons From Mutant Mouse Strains, Sherri M. Jones, Timothy A. Jones

Department of Special Education and Communication Disorders: Faculty Publications

Background

A considerable amount of research has been published about genetic hearing impairment. Fifty to sixty percent of hearing loss is thought to have a genetic cause. Genes may also play a significant role in acquired hearing loss due to aging, noise exposure, or ototoxic medications. Between 1995 and 2012, over 100 causative genes have been identified for syndromic and nonsyndromic forms of hereditary hearing loss (see Hereditary Hearing Loss Homepage http://hereditaryhearingloss.org). Mouse models have been extremely valuable in facilitating the discovery of hearing loss genes, and in understanding inner ear pathology due to genetic mutations or elucidating fundamental mechanisms …

Hearing Loss And Retarded Cochlear Development In Mice Lacking Type 2 Iodothyronine Deiodinase, Lily Ng, Richard J. Goodyear, Chad A. Woods, Mark J. Schneider

Dartmouth Scholarship

The later stages of cochlear differentiation and the developmental onset of hearing require thyroid hormone. Although thyroid hormone receptors (TRs) are a prerequisite for this process, it is likely that other factors modify TR activity during cochlear development. The mouse cochlea expresses type 2 deiodinase (D2), an enzyme that converts thyroxine, the main form of thyroid hormone in the circulation, into 3,5,3'-triiodothyronine (T3) the major ligand for TRs. Here, we show that D2-deficient mice have circulating thyroid hormone levels that would normally be adequate to allow hearing to develop but they exhibit an auditory phenotype similar to that caused by …

Recalibrating The Auditory System: A Speed–Accuracy Analysis Of Intensity Perception, Yoav Arieh, Lawrence E. Marks

Department of Psychology Faculty Scholarship and Creative Works

Recalibration in loudness perception refers to an adaptation-like change in relative responsiveness to auditory signals of different sound frequencies. Listening to relatively weak tones at one frequency and stronger tones at another make the latter appear softer. The authors showed recalibration not only in magnitude estimates of loudness but also in simple response times (RTs) and choice RTs. RTs depend on the sound intensity and may serve as surrogates for loudness. Most important, the speeded classification paradigm also provided measures of errors. RTs and errors can serve jointly to distinguish changes in sensitivity from changes in response criterion. The changes …