Healthy Voices Research Articles

Harmonic-to-noise ratio as speech biomarker for fatigue: K-nearest neighbour machine learning algorithm

BackgroundVital information about a person's physical and emotional health can be perceived in their voice. After sleep loss, altered voice quality is noticed. The circadian rhythm controls the sleep cycle, and when it is askew, it results in fatigue, which is manifested in speech. Using MATLAB statistical techniques and the k-nearest neighbour (KNN) machine learning algorithm, this study assessed the efficacy of the harmonic-to-noise ratio (HNR) as a speech biomarker in differentiating fatigued and normal voice after sleep deprivation of one night. MethodsAfter one night of sleep deprivation, acoustic samples for sustained vowel/a/and visual reaction time were recorded from n = 32 healthy young Indian male volunteers (20–40 yrs). One-way ANOVA established significant changes in voice characteristics with progressive sleep deprivation. The effectiveness of speech HNR as a biomarker for the detection of healthy and fatigued voice was researched, using the KNN classifier in a machine learning algorithm. ResultsThe HNR voice feature was taken from an acoustic sample for three times: baseline (Time 1), 3 AM (Time 2), and 7 AM (Time 3) towards an incremental one-night sleep loss. At 3AM, the HNR changed significantly p<0.05. Utilizing an iterative signal extrapolation approach, the KNN classifier divided the submitted voice signal sample into normal and fatigued categories. ConclusionThe findings imply that the HNR can be used to link fatigue from sleep deprivation with vocal alterations by classifying voice samples in a KNN classifier. Along with the multimodal diagnostic features, this method may also offer an additional acoustic biomarker for the diagnosis of fatigue post sleep loss.

Nonlinear analysis by phase space reconstruction of healthy elderly voices.

To compare the results of the non-linear acoustic analysis of elderly male and female voices, speakers of Brazilian Portuguese. Recordings of 14 men and 15 women were used. The voices were consensually judged to be vocally healthy by three trained speech therapists. The non-linear acoustic analysis was performed by the Phase Space Reconstruction (PSR) analysis using the Voice Analysis program. A significant difference was observed in the parameter irregularity (p = 0.001) and spacing (p = 0.005), with worse results for the male group. While 93% of male voices presented degrees 2 or 3 of irregularity, these degrees were observed in 53% of female voices. In 78.6% of male voices, medium to large spacing was observed, a fact observed only in 26.7% of women. The results of the non-linear analysis, through the Phase Space Reconstruction, using the CIS Protocol, in the voices of the elderly, showed the best result in terms of the number of curves (four or more). Regarding the irregularity of the tracing, in men, the majority presented grades 2 and 3 and in women, half presented grade 1. Regarding the spacing, 78.6% of the male voices had medium to large spacing, a fact observed only in 26.7% of women.There was a difference between the sexes in the vocal findings of the elderly by the CIS protocol with the PSR, pointing out worse results irregularity and spacing in the male population, which suggests greater vocal aperiodicity in elderly men.

Classification of Phonation Modes in Classical Singing Using Modulation Power Spectral Features

In singing, the perceptual term “voice quality” is used to describe expressed emotions and singing styles. In voice physiology research, specific voice qualities are discussed by the term phonation modes and are related directly to the voicing produced by the vocal folds. The control and awareness of phonation modes is vital for professional singers to maintain a healthy voice. Most studies on phonation modes have investigated speech and have used glottal inverse filtering to compute features from an estimated excitation signal. The performance of this method is reported to decrease at high pitches, which limits its usability for the singing voice. To overcome this, this study proposes to use features derived from the modulation power spectrum for phonation mode classification in the singing voice. The exploration of the modulation power spectrum is motivated by the fact that, in singing, temporal modulations (known as vocal vibrato) and spectral modulations hold information of the vocal fold tension. Since there exists no large publicly available dataset of phonation modes in singing, we created a new dataset consisting of six female and four male classical singers, who sang five vowels at different pitches in three phonation modes (breathy, modal, and pressed). Experimental results with a support vector machine classifier reveal that the proposed features show better classification performance compared to state-of-the-art reference features. The performance for the current dataset is at least 10% higher compared to the performance of the reference features (such as glottal source features and MFCCs) in the case of target labels and around 6% higher in the case of perceptually assessed labels.

A Cepstral Analysis of Pathological Voice Quality in the Korean Population using Praat

This study aimed to investigate the reference values for cepstral peak prominence (CPP) and smoothed CPP (CPPS) measured using Praat in Korean speakers with the normal, healthy and pathological voice. A total of 4,524 Korean participants with vocally healthy (n=410) and dysphonic voices (n=4,114) participated in this study. The speech task consisted of a sustained vowel /a/ and a sentence reading the Korean passage "Walk". CPP and CPPS values were quickly and automatically measured in sustained vowel and continuous speech tasks using Praat script. Furthermore, three veteran speech language pathologists (SLPs) scored the severity of dysphonia using the GRBAS scale (grade, roughness, breathiness, asthenia, strain) and Consensus Auditory Perceptual Evaluation of Voice (CAPE-V). Three SLPs showed high inter- and intra-rater reliabilities (IRR) in auditory-perceptual (A-P) evaluation. Significant differences were confirmed in CPP and CPPS between the normally healthy and pathological voice groups for both voice tasks (P < 0.01). The measured values of CPP and CPPS varied depending on the laryngeal pathology. In the receiver operating characteristic (ROC) curve analysis, the CPP_Vowel (CPP_V), CPPS_V, CPP_Sentence (CPP_S), and CPPS_S cut-off values were <21.5, <12.0, <19.7, and <10.1, respectively. Through ROC curve analysis, it was confirmed that CPP and CPPS had excellent diagnostic accuracy in distinguishing disordered voice (area under the ROC: 0.951-0.966). We investigated the reference values for CPP and CPPS measured with Praat for Korean speakers and confirmed that cepstral analysis is a promising tool for differentiating pathological voice.

Exploring the mechanics of fundamental frequency variation during phonation onset.

Fundamental frequency patterns during phonation onset have received renewed interest due to their promising application in objective classification of normal and pathological voices. However, the associated underlying mechanisms producing the wide array of patterns observed in different phonetic contexts are not yet fully understood. Herein, we employ theoretical and numerical analyses in an effort to elucidate the potential mechanisms driving opposing frequency patterns for initial/isolated vowels versus vowels preceded by voiceless consonants. Utilizing deterministic lumped-mass oscillator models of the vocal folds, we systematically explore the roles of collision and muscle activation in the dynamics of phonation onset. We find that an increasing trend in fundamental frequency, as observed for initial/isolated vowels, arises naturally through a progressive increase in system stiffness as collision intensifies as onset progresses, without the need for time-varying vocal fold tension or changes in aerodynamic loading. In contrast, reduction in cricothyroid muscle activation during onset is required to generate the decrease in fundamental frequency observed for vowels preceded by voiceless consonants. For such phonetic contexts, our analysis shows that the magnitude of reduction in the cricothyroid muscle activation and the activation level of the thyroarytenoid muscle are potential factors underlying observed differences in (relative) fundamental frequency between speakers with healthy and hyperfunctional voices. This work highlights the roles of sometimes competing laryngeal factors in producing the complex array of observed fundamental frequency patterns during phonation onset.

How to speak and vocal hygiene.

An abnormal tongue shape, pitch difference or voice quality can lead to difficulty communicating effectively. Common among teachers are voice issues, which can be uncomfortable and make it challenging to carry out daily tasks and work-related activities. 1 Teacher who suffers from voice disorders may have trouble communicating clearly with their students. Voice disorders affect negatively a teacher's ability to communicate effectively throughout the day and their emotions, leading them to feel inadequate and frustrated at times. Voice misuse is inappropriate voice usage. It includes speaking involving hard glottal attacks and cheerleading for an extended period. 2 Vocal abuse is defined as activities having a detrimental effect on the larynx and voice. These include yelling and screaming, excessive talking or singing, excessive talking with an upper respiratory infection or allergy. It is important to identify and reduce the phono traumatic behaviours (for example loud voice use, speaking over background noise, throat clearing, cheering and screaming, and unconventional voice production), awareness about the vocal mechanism, and address high-risk situations associated with speech. In addition, it involves controlling how much you talk, monitoring your pitch and intensity (The speech of a typical adult male will have a basic frequency from 85 to 155 Hz, and a typical adult female ranges from 165 to 255 Hz.) 3 and conserving your voice by resting it. A healthy voice is dependent upon several factors, including local lubrication (About 15.5 cups (3.7 litres) of fluids per day are recommended for men. 11.5 cups (2.7 litres) of fluids per day is recommended for women)4, necessary dietary choices; as well as eliminating the effect of medications, environment, and healthy lifestyle choices (reduction of alcohol, recreational drugs, tobacco, and caffeinated beverages,). 5.Voice hygiene has two primary goals: to improve communication effectiveness and to promote vocal health. Additionally, by fostering optimal vocal habits as a precautionary measure, your voice will be maintained healthily, reducing the risk of vocal injury. Voice hygiene awareness can help all professionals, especially teachers, to maintain voice quality. We believe regular voice use is a right of every individual, and understanding is needed to make people aware of voice disorders and how to prevent them. As professionals, we can assist and help out people with voice disorders or professionals at risk of acquiring voice disorders to rule out possible causes and treatment strategies.

Recognition of the Effect of Vocal Exercises by Fuzzy Triangular Naive Bayes, a Machine Learning Classifier: A Preliminary Analysis

Machine learning (ML) methods allow the development of expert systems for pattern recognition and predictive analysis of intervention outcomes. It has been used in Voice Sciences, mainly to discriminate between healthy and dysphonic voices. Parameter patterns of vocal acoustic analysis and vocal perceptual assessment can be evaluated by ML classifiers, such as the Fuzzy Triangular Naive Bayes (FTriangNB), after using techniques that improve the vocal quality of individuals with healthy or dysphonic voices. Thus, the goal of this study was to analyze the performance of the FTriangNB to detect patterns in the acoustic parameters and the auditory-perceptual assessment of 12 women with dysphonia and 12 vocally healthy women, after performing three vocal exercises (tongue trills, semi-occluded vocal tract exercise with a high-resistance straw - SOVTE, and over-articulation). The FTriangNB classifier contained in the Fuzzy Class package was implemented in the data analysis software R Studio version 1.4.1106 for Macintosh. The confusion matrix was extracted, as well as the accuracy, the Kappa coefficient, and the class statistics. The final result was compared with those generated by FTriangNB with the same variables from the preapplication database of the exercises. The FTriangNB presented good accuracy (87.5%) and Kappa coefficient (81.3%), and showed almost perfect agreement after application of the exercises, while the results before the application of the exercises demonstrated accuracy without acceptable discrimination capacity (33.3%) and Kappa coefficient with a poor agreement (-6.67%). The Semioccluded Vocal Tract Exercises(SOVTE) with high strength straw presented with a sensitivity and Negative Predictive Value (NPV) of value 1 (one), and the over-articulation's specificity and Positive Predictive Value (PPV) also showed a value of 1 (one). The FTriangNB showed great accuracy in recognizing the effect of vocal exercises. Exploratory studies with larger samples using FTriangNB, as well as other Machine Learning classifiers should be further carried out for this purpose in the Voice Science to enable inferences.

Reflections: Being an Eyewitness to Vocal Music History

Being an Eyewitness to Vocal Music History Kimberly Broadwater (bio) PROVENANCE prov·e·nance (prǒv´ ə nəns) n. Place of origin, source. [Lat. Provenire, to originate.] Eyewitness misidentifications are known to have played a role in 70 percent of the 349 wrongful convictions that have been overturned based on DNA evidence.1 If you are a connoisseur of law enforcement movies or television shows, you probably have seen a scene where the victim of a crime mistakenly selects an innocent person based solely on their own recognitions. The erroneously selected subject can be convicted merely on the words of the victim. However, over time experts have been able to document that eyewitnesses are not always the most reliable source of information. Experimental social psychologist Gary Wells told reporter Zak Stambor, "Like trace evidence, eyewitness evidence can be contaminated, lost, destroyed or otherwise made to produce results that can lean to an incorrect reconstruction of the crime."2 Contamination of eyewitness evidence can be affected by multiple variables, including: • diminished capacity (alcohol, drug use, exhaustion, etc.); • age; • sex; • predetermined biases; • time and distance away from the event; • instructions given to the eyewitness. Informed scientists, psychologists, and law enforcement have researched the reliability of eyewitness identification and have begun to create protocols and standards that have increased the reliability of eyewitness testimony. For instance, Klobuchar, Steblay, and Caliguiri discovered that "blind sequential identification procedures" was effective in reducing the potential for misidentifications (blind: law enforcement do not know which person in the "lineup" is the accused; sequential: eyewitnesses are shown the "lineup" one person at a time.)3 The Oxford Companion to Music defines music criticism as "the intellectual activity of formulating judgments on the value and degree of excellence of individual works of music, or whole groups or genres."4 Musicologist Winton Dean (1916–2013) stated, "music is probably the most difficult of the arts to criticize."5 (Point of personal privilege: using this quotation finds me at a moment of ambiguity, in that I had a professor who would not allow students to quote Winton Dean because they felt Dean based much of his research on opinion and not fact.) [End Page 243] Musicologists and music critics can be compared to eyewitnesses. If I were to witness a concert by a well known singer and wrote a review, I would be presenting my interpretation of the concert. Would it matter that the singer chose music that was not to my liking? Would it matter that the collaborative pianist hummed along with the performer? If I prefer a healthy chest voice and the performer had a lighter quality, would my preference affect my opinion? Regardless, if I write my interpretation down on paper, I have recorded "history." The old maxim "History is written by victors" does have relevance. We all have preconceived biases that lead our interpretations, and quite often our observations are more "commentary" than "news." In the early twentiety century, many singing teachers would market themselves as teachers of "So-and-So's Method." The consumer did not know if the advertised teacher personally worked with Professor So-and-So or had attended one master class and self-proclaimed as expert. Fortunately, today we have more legitimate ways of verifying credentials. We, as teachers of singing, should consider any source that purports to espouse the teaching method of another as suspect until we can establish the credentials of said teacher. For an example, I offer the teachings of Dr. Stephen Austin, a mentor and friend (and I am probably providing this example with my own internal biases). Dr. Austin often leads workshops and master classes, teaching from the precepts of Manuel Garcia (1805–1906). I have first hand knowledge of Dr. Austin's intimate relationship with Garcia's writings and teachings and am left with little doubt that he is an expert on the subject matter, able to quote "scripture and verse." This is not to say that Dr. Austin sat at the feet of Garcia taking copious notes as he observed the master teacher employing his methodology. However, Dr. Austin has taken the time to consider opposing views of the teachings of Garcia, has scrutinized...

Students’ Experience with Vocal Injury in Undergraduate Performing Arts Training Programs

Voice injuries are well-documented in the literature and can be found in any person regardless of their profession. However, performing artists need a healthy voice in order to do their job properly. In educational environments, students with injuries are presented with the unique challenge of recovery in addition to a heavy course load. This study seeks to understand and question the experience of the undergraduate vocally injured performing arts student. An IRB approved, online survey was created to assess vocally injured undergraduate students' experiences and was shared via social media and email outreach. The results of this study show clear ways that undergraduate faculty can support their injured students while they are in training. Additional findings include the importance of the voice teacher/student relationship, timing of diagnoses, and the overall faculty dynamic. Future research may benefit from investigating the voice teacher/student relationship and the mental health repercussions of vocally injured performing arts students. In conclusion, this study found that vocally injured students have diverse experiences while in undergraduate training programs.

Rethinking Activity: Development And Implementation Of A Virtual Self-management Program For People Living With Long COVID-19

PURPOSE: A subset of people who contract COVID-19 will continue to experience symptoms for months after the infection, a phenomenon known as long COVID. Long COVID is an episodic health condition with symptoms (such as dyspnea, fatigue, and post-exertional symptom exacerbation) that last for at least two months that cannot be explained by an alternative diagnosis. The likely volume of current and future long COVID patients in Canada is so high that primary care may not be able to cope given current resources. Many patients are struggling, and more support for self-management of symptoms and activities is required. METHODS: Individuals living with long COVID were recruited using clinical and patient-oriented networks. The BREATHE program is a free, virtual, multidisciplinary, patient-centred, group-based self-management program for long COVID that provides education on Breathing, Rest/recovery, Education, Activity management, Thinking/cognition, Healthy voice strategies, and Eating/nutrition. Group sessions include breakout room discussions on activity pacing and reframing exercise. Content is based on clinical experience, evidence from other conditions and the recommendations for safe rehabilitation in people living with long COVID. Three cohorts of adults living with long COVID took part in March, May and August 2021. Data on recruitment and attendance were collected, and anonymous patient feedback was collected for the purpose of quality improvement. RESULTS: Across the three cohorts, group sizes were n = 8 (an initial pilot), n = 16, and n = 16, and overall attendance was 90%, 91%, and 86%, respectively. There were 3 withdrawals, and feedback was received from 28 individuals. The program was significantly modified in response to patient priorities and preferences, and therapeutic relationships and peer support were emphasized. BREATHE is now an eight-week program involving two sessions per week. Feedback has been increasingly positive, and 100% of respondents from the most recent cohort found BREATHE helpful and would recommend it to other people with long COVID. CONCLUSIONS: The BREATHE self-management program is a feasible, potentially beneficial and cost-effective supportive care strategy for people living with long COVID that could be adopted within the healthcare system.

The Immediate and Long-Term Effects of Tube and Mask+Tube Phonation in Water Exercises and Their Duration as Measured by Electroglottographic and Nasometric Parameters

This study investigated the immediate effects and their persistence (at 15 minutes) of various durations of semi-occluded vocal tract exercise (SOVTE) (standard tube into water and modified mask+tube into water exercises) as measured by electroglottographic (EGG) and nasometric parameters. The study included 30 women aged 19 through 28 years with healthy voices, and it comprised five randomly implemented procedures (Ps): P1-tube phonation into water for 5 minutes; P2-tube phonation into water for 10 minutes; P3-tube+ventilation mask phonation into water for 5 minutes; P4-tube+ventilation mask phonation into water for 10 minutes; P5-phonation with ventilation mask for 5 minutes. Fifteen-minute voice rest breaks were provided between each procedure. Nasometric and electroglottographic measurements were taken before, during, immediately after and at 5, 10, and 15 minutes after the exercises, and the recorded measurements were analyzed. The immediate effects of P3 and P4 on voice quality showed better performance than the other procedures. Among all the procedures, P1 had the smallest effect on voice quality in terms of nasometric and EGG parameters and the least degree of effect permanence. In all the fluctuating SOVTE procedures except P1, the nasalance scores decreased (P1, P2, P3, and P4: fluctuating SOVTE; P5: steady SOVTE). The tube phonation exercises modified by the addition of a ventilation mask were highly advantageous in terms of EGG parameters. In addition to this, regardless of the mode of application of the retention time, it was observed that the positive effect (ie, lower vertical laryngeal position) of the exercises applied for 10 minutes was higher than the exercises applied for 5 minutes.

Performance of Acoustic Measures for the Discrimination Among Healthy, Rough, Breathy, and Strained Voices Using the Feedforward Neural Network

To identify and evaluate the best set of acoustic measures to discriminate among healthy, rough, breathy, and strained voices. This study used the vocal samples of the sustained /ε/ vowel from 251 patients with the vocal complaints, among which 51, 80, 63, and 57 patients exhibited healthy, rough, breathy, and strained voices, respectively. Twenty-two acoustic measures were extracted, and feature selection was applied to reduce the number of combinations of acoustic measures and obtain an optimal subset of measures according to the information gain attribute ranking algorithm. To classify signals as a function of predominant voice quality, a feedforward neural network was applied using a Levenberg-Marquardt supervised learning algorithm. The best results were obtained from 11 combinations, with each combination presenting six acoustic measures. Kappa indices ranged from 0.7527 to 0.7743, the overall hit rates are 81.67%-83.27%, and the hit rates of healthy, rough, breathy, and strained voices are 74.51%-84.31%, 78.75%-90.00%, 85.71%-98.41%, and 68.42%-82.46%, respectively. We obtained the best results from 11 combinations, with each combination exhibiting six acoustic measures for discriminating among healthy, rough, breathy, and strained voices. These sets exhibited good Kappa performance and a good overall hit rate. The hit rate varied between acceptable and good for healthy voices, acceptable and excellent for rough voices, good and excellent for breathy voices, and poor and good for strained voices.

Videokymogram Analyzer Tool: Human–computer comparison

Videokymography (VKG) is a modern video recording technique used in laryngology and phoniatrics to examine vocal fold vibrations. To obtain quantitative information on the vocal fold vibration, VKG image analysis is needed but no software has yet been validated for this purpose. Here, we introduce a validated software tool that aids clinicians to evaluate diagnostically important vibration characteristics in VKG and other types of kymographic recordings. State-of-the-art methods for automated image evaluation were implemented and tested on a set of videokymograms with a wide range of vibratory characteristics, including healthy and pathologic voices. The automated image segmentation results were compared to manual segmentation results of six evaluators revealing average differences smaller than one pixel. Furthermore, the automatically categorized vibratory parameters precisely agreed with the average visual assessment in 84 and 91 percent of the cases for pathological and healthy patients, respectively. Based on these results, the newly developed software was found to be a valid, reliable automated tool for the quantification of vocal fold vibrations from VKG images, offering a number of novel features relevant for clinical practice.

Automatic Speech Recognition on Non-Pathological Dataset of Urdu Language

One of its subsystems, speech, has a strong underlying characteristic and a distinct voice. Voice disorders are abnormal conditions that influence the quality of voice. Several protocols, including acoustic analysis, can detect clinical voice pathology. Based on a computerized acoustic analysis, machine learning algorithms and non-invasive systems may play a very vital part in initial detection, tracking, and even growth of proficient pathological speech analysis. The aim of this research paper is to collect a non-pathological dataset i.e. healthy voice dataset. Two important and critical features; 1) MFCC and 2) Pitch are used to generate a final audio clip. SVM used as a classifier to train and test the dataset model and the models exhibited reasonably high training and testing accuracies i.e. 85.886% which proves to be a milestone on Urdu language dataset.

Association between voice symptoms and college professors’ home working conditions during online classes in times of COVID-19 pandemic

Introduction. Due to the COVID-19 pandemic, teaching conditions changed around the world from in-person classes to online classes, which also determined changes on teachers’ working conditions. Method: Exploratory cross-sectional study with the aim of determining the association between two voice symptoms (vocal fatigue and throat pain) with home working conditions during online classes in times of COVID-19 pandemic. Professors answered an online survey including 27 questions about four components: sociodemographic factors, characteristics of home working, quarantine characteristics, and health conditions (including voice functioning). Results: 177 college professors from Argentina, Colombia, and Chile participated in this study. First, incidence of vocal fatigue, during online classes in times of COVID-19 pandemic, represented around 50%. Although throat pain had a smaller incidence, it was also important (35%). Second, days in quarantine, number of classes per week, people living with during quarantine, and history of vocal fatigue before quarantine were important associated factors of vocal fatigue. Third, important associated factors of throat pain were number of classes per week, level of stress, years of experience, and history of throat pain before quarantine. Conclusion: Similar to pre-COVID-19, vocal fatigue and throat pain were frequently reported voice symptoms among college professors. Associated factors of these symptoms included years of experience, number of classes per week, stress, people living with during quarantine due to COVID-19, and history of voice symptoms. Workplace Health Promotion programs should include activities that facilitate a healthy occupational voice use during and post-COVID-19 pandemic, considering the implications of online teaching on teachers’ health and safety.

Knowledge of Egyptian faculty members about voice care: a national cross-sectional study

BackgroundThe university teaching faculty members are one of the occupational fields in education that are more exposed to voice disorders. The current study aimed to examine the association among vocal symptoms reported by faculty teaching professionals, impact of voice problems on daily activities, their vocal habits, and knowledge on vocal hygiene in relation to specialist consultation and to identify which of the assessed factors triggered the most for medical consultation. An online questionnaire was completed by 420 faculty teaching professionals from 7 universities in Egypt between November 2019 and December 2019.ResultsAll assessed vocal symptoms were significantly associated with specialist consultation (p-value <0.01). Most common bad vocal habits included increased voice loudness (71.2%), talking for long time (69.3%), and frequent throat clearance (54.0%). The most commonly reported preventive measures included avoid screaming (88.3%), stop smoking (87.1%), and taking periods of voice rest (86.4%). The strongest predictor of having specialist consultation was frequent throat clearance, recording an odds ratio of 23.809.ConclusionBased on information obtained from the current study, ideas are suggested for setting up vocal hygiene programs throughout a professional voice career for keeping a healthy voice. Avoid passive smoking and using microphones are considered remarkable adequate methods for healthy voice.

Reliability of the Acoustic Voice Quality Index AVQI and the Acoustic Breathiness Index (ABI) when wearing CoViD-19 protective masks

PurposeInvestigating whether the Acoustic Voice Quality Index (AVQI) and the Acoustic Breathiness Index (ABI) are valid and comparable to previous unmasked measurements if the speaker wears a surgical mask or a FFP-2 mask to reduce the risk of transmitting air-borne viruses such as SARS-CoV-2.MethodsA convenience sample of 31 subjectively healthy participants was subjected to AVQI and ABI voice examination four times: Twice wearing no mask, once with a surgical mask and once with a FFP-2 mask as used regularly in our hospital. The order of the four mask conditions was randomized. The difference in the results between the two recordings without a mask was then compared to the differences between the recordings with each mask and one recording without a mask.ResultsSixty-two percent of the AVQI readings without a mask represented perfectly healthy voices, the largest AVQI without a mask value was 4.0. The mean absolute difference in AVQI was 0.45 between the measurements without masks, 0.48 between no mask and surgical mask and 0.51 between no mask and FFP-2 mask. The results were neither clinically nor statistically significant. For the ABI the resulting absolute differences (in the same order) were 0.48, 0.69 and 0.56, again neither clinically nor statistically different.ConclusionBased on a convenience sample of healthy or only mildly impaired voices wearing CoViD-19 protective masks does not substantially impair the results of either AVQI or ABI results.

How older adults relate to their own voices: a qualitative study of subjective experiences of the aging voice

Aim The aim of this study was to investigate how otherwise healthy older adults with self-assessed voice problems relate to their voice and voice changes. Method Focus groups were conducted at an activity center to identify how older adults reflect on their own voice and the aging voice in general. The interviews were audio recorded and transcribed. The analysis was done using thematic content analysis. Results The analysis resulted in three main themes: “communicational aspects of the aging voice,” “consequences of deteriorating vocal and communicative capacity,” and “attitudes, strategies, and ideas”. The participants considered voice to be an important communication tool and presented what could be interpreted as awareness regarding their voice. Voice changes were considered a natural part of aging. This attitude was also an important reason why the participants had not sought medical care for their voice problems. The participants discussed ideas concerning extended voice use to maintain a functioning voice when aging. Simultaneously, voice changes due to aging were considered to have a negative effect on communication and social participation. Conclusions The voice is important for older adults, and an insufficient voice can affect communication and social participation. Information about aging voice and voice exercises, for example from speech language pathologists, could be of interest among older adults. Further studies on the voice of older adults are needed regarding how they experience their voice and the general aspects of a healthy aging voice.

An Analytical Study of Speech Pathology Detection Based on MFCC and Deep Neural Networks.

Diseases of internal organs other than the vocal folds can also affect a person's voice. As a result, voice problems are on the rise, even though they are frequently overlooked. According to a recent study, voice pathology detection systems can successfully help the assessment of voice abnormalities and enable the early diagnosis of voice pathology. For instance, in the early identification and diagnosis of voice problems, the automatic system for distinguishing healthy and diseased voices has gotten much attention. As a result, artificial intelligence-assisted voice analysis brings up new possibilities in healthcare. The work was aimed at assessing the utility of several automatic speech signal analysis methods for diagnosing voice disorders and suggesting a strategy for classifying healthy and diseased voices. The proposed framework integrates the efficacy of three voice characteristics: chroma, mel spectrogram, and mel frequency cepstral coefficient (MFCC). We also designed a deep neural network (DNN) capable of learning from the retrieved data and producing a highly accurate voice-based disease prediction model. The study describes a series of studies using the Saarbruecken Voice Database (SVD) to detect abnormal voices. The model was developed and tested using the vowels /a/, /i/, and /u/ pronounced in high, low, and average pitches. We also maintained the “continuous sentence” audio files collected from SVD to select how well the developed model generalizes to completely new data. The highest accuracy achieved was 77.49%, superior to prior attempts in the same domain. Additionally, the model attains an accuracy of 88.01% by integrating speaker gender information. The designed model trained on selected diseases can also obtain a maximum accuracy of 96.77% (cordectomy × healthy). As a result, the suggested framework is the best fit for the healthcare industry.

Relationship Between Oropharyngeal Geometry and Vocal Parameters in Subjects With Parkinson's Disease

To verify whether the dimensions of different segments of the oropharyngeal cavity have different proportions between Parkinson's disease patients and vocally healthy subjects and investigate whether the measurements of these subjects' oropharyngeal geometry associate with their acoustic measurements of voice. Quantitative, descriptive, cross-sectional, and retrospective study with secondary data, approved by the Human Research Ethics Committee under no. 4.325.029. We used vocal samples and data from the oropharyngeal geometry of 40 subjects - 20 with Parkinson's disease stages I to III and 20 who formed the control group, matched for sex and age. Each group had 10 males and 10 females, mean age of 61 years (±6.0). Formant (F1, F2, and F3) and cepstral measures of the sustained vowel /ε/ were extracted and arranged in the database to determine their values using Praat software. The data were descriptively analyzed, with statistics generated with R software. The proportion of oropharyngeal geometry measurements was arranged by mean values and coefficients of variation. Pearson's linear correlation test was applied to relate voice parameters to oropharyngeal geometry, considering P < 0.05, and linear regression test, to justify F2. The Parkinson's disease group showed a linear relationship between oral cavity length and F1 in males (P = 0.04) and between glottal area and F2 in females (P = 0.00); linear relationships were established according to age in both groups, and a regression model for F2 was estimated (R2 = 0.61). There was no difference between pathological and healthy voices; there was a difference in the proportional relationship of oropharyngeal geometry between the groups. The proportional relationship of oropharyngeal geometry differs between the Parkinson's disease group and the control group, as well as the relationship between oropharyngeal geometry and formant and cepstral values of voice according to the subjects' sex and age.