Voice Quality Assessment Research Articles

Demystifying Velopharyngeal Dysfunction for Plastic Surgery Trainees Part 2: Speech Fundamentals and Perceptual Speech Assessment.

Velopharyngeal dysfunction (VPD) is the inability to achieve proper closure of the velopharyngeal (VP) port, affecting speech and swallowing. The gold standard for diagnosis is auditory-perceptual speech evaluation by a specialized speech-language pathologist. This 3-part series provides a comprehensive discussion on (1) the anatomy and physiology of the velopharyngeal mechanism, (2) fundamental speech terminology and principles of perceptual speech assessment for VPD, and (3) techniques for objective evaluation of the VP port and surgical decision-making process. In part 2, the authros begin with the concepts and terminology required to understand the perceptual speech assessment of VPD, including resonance, articulation, and the differentiation between consonants and vowels. We review the types of speech samples used for evaluation such as single-word articulation tests, syllable repetition, sentence repetition, and spontaneous connected speech. Finally, we discuss the auditory-perceptual speech assessment for VPD, including the assessment of resonance, nasal air emission, articulation, and voice quality. The use of rating scales like the Pittsburgh Weighted Speech Scale (PWSS) and the Cleft Audit Protocol for Speech-Augmented-Americleft Modification (CAPS-A-AM) is highlighted. In addition, the significance of intraoral examinations, visual-tactile-auditory evaluations, and the assessment of voice quality are covered. Most textbook chapters discussing this topic assume a foundational knowledge of speech-language pathology, which a surgical trainee may lack. This study aimed to bridge the gap between surgical training and speech pathology, providing a comprehensive resource to enhance the understanding and management of VPD.

HEAR set: A ligHtwEight acoustic paRameters set to assess mental health from voice analysis

BackgroundVoice analysis has significant potential in aiding healthcare professionals with detecting, diagnosing, and personalising treatment. It represents an objective and non-intrusive tool for supporting the detection and monitoring of specific pathologies. By calculating various acoustic features, voice analysis extracts valuable information to assess voice quality. The choice of these parameters is crucial for an accurate assessment. MethodIn this paper, we propose a lightweight acoustic parameter set, named HEAR, able to evaluate voice quality to assess mental health. In detail, this consists of jitter, spectral centroid, Mel-frequency cepstral coefficients, and their derivates. The choice of parameters for the proposed set was influenced by the explainable significance of each acoustic parameter in the voice production process. ResultsThe reliability of the proposed acoustic set to detect the early symptoms of mental disorders was evaluated in an experimental phase. Voices of subjects suffering from different mental pathologies, selected from available databases, were analysed. The performance obtained from the HEAR features was compared with that obtained by analysing features selected from toolkits widely used in the literature, as with those obtained using learned procedures. The best performance in terms of MAE and RMSE was achieved for the detection of depression (5.32 and 6.24 respectively). For the detection of psychogenic dysphonia and anxiety, the highest accuracy rates were about 75 % and 97 %, respectively. ConclusionsThe comparative evaluation was carried out to assess the performance of the proposed approach, demonstrating a reliable capability to highlight affective physiological alterations of voice quality due to the considered mental disorders.

Survey of Voice-Focused Speech-Language Pathologists’ Usage of the Consensus Auditory Perceptual Evaluation of Voice (CAPE-V)

PurposeAs part of the process of developing specific recommendations for modifying certain elements of the Consensus Auditory Perceptual Evaluation of Voice (CAPE-V)to promote end-user fidelity, the authors sought input from voice clinicians who regularly use the CAPE-V to assess voice quality. MethodAt an academic meeting focusing on voice disorders, we presented a poster briefly reviewing the CAPE-V protocol and describing several sources of variability that have been reported in its current use. Interested viewers were directed to a QR code linking to a brief, anonymous survey on how individuals currently use the CAPE-V and how they might improve it. A link to the survey was also distributed on the conference discussion board. ResultsFifty-nine participants responded to the survey; 49 completed it. The median respondent reported 8 years of experience conducting voice evaluations, with 50% of their current practice in voice, and about 8 voice evaluations per week. Key findings from this survey were that fewer than half of respondents reported audio recording any components of in-person or virtual voice evaluations, and that most respondents reported changing some aspect of the CAPE-V tasks and stimuli in practice. ConclusionThis exploratory study revealed a wide range of idiosyncratic practices by clinicians when administering and scoring the CAPE-V. Findings support planned revisions to the CAPE-V protocol and form involving the tasks, stimuli and rating procedures.

Adaptation and Validation of the Persian Version of the Voice Handicap Index-10 (VHI-10)

ObjectivesVoice disorders can profoundly impact health, quality of life, job performance, and social interactions. Traditional evaluations have expanded to include quality-of-life assessments, emphasizing self-reported outcomes. The Voice Handicap Index (VHI) stands out among relevant questionnaires, with the VHI-10 being a concise derivative. This study was conducted to translate and validate the Voice Handicap Index-10 (VHI-10) questionnaire for Persian speakers, enhancing clinical assessments of voice disorders and quality of life. MethodsThis cross-sectional study, conducted in Iran, involved (1) translating the VHI-10 into Persian, (2) confirming face and content validity using Content Validity Ratio (CVR), and Content Validity Index (CVI), and (3) evaluating its reliability through a survey. A panel of experts confirmed the validity, and reliability of the study, which was assessed using Cronbach's alpha, Spearman-Brown, and Guttman coefficients. The survey involved 225 participants, including 150 healthy people and 75 patients with voice disorders, who were selected using a convenience sampling method. ResultsAll question items demonstrated a CVI greater than 0.79 and a CVR between 0.62 and 1. Reliability analysis yielded high Cronbach's alpha values for functional, physical, and emotional domains (0.909) and total (0.961). The mean overall scores of VHI-10 for healthy and disordered groups were 18.78 and 0.74, respectively. The VHI-10 effectively discriminated between healthy and disordered groups in all domains, with an accuracy of 97.33%. The determined cut-off point was 4.5, with a strong area under the ROC curve (0.989). ConclusionThis study successfully adapted and validated the Persian version of the VHI-10. The questionnaire demonstrated high reliability and validity, distinguishing between individuals with and without voice disorders. This Persian version is now a valuable tool for speech and language pathologists conducting clinical voice evaluations in Iran and also it could be applied in studies to determine the effects of voice problems on participant's quality of life.

Robust constrained cosine arctangent based adaptive filtering for feedback control in hearing aids

The striking problem of acoustic feedback remains a persistent challenge in hearing aids (HAs), imposing limitations on attainable amplification and significantly deteriorating sound quality, often manifesting as disruptive howling artifacts. With the objective of feedback mitigation, the feedback path is estimated using an adaptive filter. The constrained least mean square (CLMS) technique is commonly employed in adaptive filtering applications where it is necessary to meet specific linear constraints. However, algorithm's robustness is compromised when impulsive or non-Gaussian noise interference occurs. In lieu of this, a novel algorithm known as the robust constrained cosine arctangent (CCAT) adaptive filtering is introduced to enhance the convergence behavior. This has been formulated with the inclusion of linear constraints to the suggested cosine function integrated with the arctangent technique. This algorithm aims to address the issue of feedback cancellation in hearing aids along a set of constraints. To achieve a minimal steady-state error and expedite the convergence of the method, a novel policy that adjusts the step factor has been suggested. CCAT-VSS is a modified version of CCAT that includes a variable step size (VSS). The simulation findings demonstrate that the suggested method exhibits superior performance for misalignment, added stable gain and certain voice quality assessments.

Evaluation of Voice Therapy After Type I, II, and V Cordectomy for Early-Stage Laryngeal Cancer Using Subjective Voice Quality Assessment Tools.

Evaluation of Voice Therapy After Type I, II, and V Cordectomy for Early-Stage Laryngeal Cancer Using Subjective Voice Quality Assessment Tools.

Assessment of Voice Quality and Vocal Cord Paralysis After Endarterectomy.

Recurrent laryngeal nerve palsy is a rare but important complication after endarterectomy (CEA). The impact on voice quality after this procedure is also important. The aim of the study was to assess voice quality and vocal cord function after CEA. 200 patients were enrolled in the study. Inclusion criteria were indications for CEA and patient consent to the procedure. Endoscopic examination of the larynx was performed before the procedure, immediately after the procedure, on the 2nd day after the procedure, then 3 month and 6 months after the procedure. Voice was assessed by maximum phonation time (MPT), GRBAS scale, Voice Handicap Index (VHI) and the Voice-Related Quality of Life (V-RQOL) questionnaire. In the study group, the results on the GRBAS scale were significantly worse and the average MPT was shorter compared to the control group. In the V-RQOL assessment, patients rated their voice as fair or good, significantly more often noticed that they had difficulty speaking loudly and being heard, and that they felt short of air when speaking. In VHI-30, the total score was significantly higher in the study group compared to the control group. Voice disorders after the procedure were reported by 68 patients, while a disorder of the recurrent laryngeal nerve was observed immediately after the procedure in 32 patients. Most vocal cord disorders were transient. Ultimately, 3% of patients were diagnosed with vocal cord paralysis. Cranial nerves paralysis, including the recurrent laryngeal nerve, are a common complication after CEA. Majority the paralysis is transient, but requires appropriate diagnostic and therapeutic procedures. Vocal cord evaluation is a non-invasive and widely available examination and should be performed pre- and postoperatively after all neck surgeries. The incidence of voice disorders after CEA significantly affects the quality of life of patients and requires voice rehabilitation and patient care with psychological support.

Comparison of Voice Cloning Algorithms in Zero-shot and Few-shot Scenarios

Voice cloning technology has made significant strides in recent years, with applications ranging from personalized virtual assistants to sophisticated entertainment systems. This study compares nine voice cloning models, focusing on both zero-shot and fine-tuned approaches. Zero-shot voice cloning models have gained attention for their ability to generate high-quality synthetic voices without requiring extensive training data for each new voice and for their capability to perform real-time inference online. In contrast, non-zero- shot models typically require additional data but can offer improved fidelity in voice reproduction. The study comprises two key experiments. The first experiment evaluates the performance of zero-shot voice cloning models, analyzing their ability to reproduce target voices without prior exposure accurately. The second experiment involves fine-tuning the models on target speakers to assess improvements in voice quality and adaptability. The models are evaluated based on key metrics assessing voice quality, speaker identity preservation, and subjective and objective performance measures. The findings indicate that while zero-shot models offer greater flexibility and ease of deployment, fine-tuned models can deliver superior performance.

Comparison of Voice Cloning Algorithms in Zero-shot and Few-shot Scenarios

Voice cloning technology has made significant strides in recent years, with applications ranging from personalized virtual assistants to sophisticated entertainment systems. This study compares nine voice cloning models, focusing on both zero-shot and fine-tuned approaches. Zero-shot voice cloning models have gained attention for their ability to generate high-quality synthetic voices without requiring extensive training data for each new voice and for their capability to perform real-time inference online. In contrast, non-zero- shot models typically require additional data but can offer improved fidelity in voice reproduction. The study comprises two key experiments. The first experiment evaluates the performance of zero-shot voice cloning models, analyzing their ability to reproduce target voices without prior exposure accurately. The second experiment involves fine-tuning the models on target speakers to assess improvements in voice quality and adaptability. The models are evaluated based on key metrics assessing voice quality, speaker identity preservation, and subjective and objective performance measures. The findings indicate that while zero-shot models offer greater flexibility and ease of deployment, fine-tuned models can deliver superior performance.

Descriptor: Voice Pre-Processing and Quality Assessment Dataset (VPQAD)

Descriptor: Voice Pre-Processing and Quality Assessment Dataset (VPQAD)

Machine learning based estimation of hoarseness severity using sustained vowelsa).

Auditory perceptual evaluation is considered the gold standard for assessing voice quality, but its reliability is limited due to inter-rater variability and coarse rating scales. This study investigates a continuous, objective approach to evaluate hoarseness severity combining machine learning (ML) and sustained phonation. For this purpose, 635 acoustic recordings of the sustained vowel /a/ and subjective ratings based on the roughness, breathiness, and hoarseness scale were collected from 595 subjects. A total of 50 temporal, spectral, and cepstral features were extracted from each recording and used to identify suitable ML algorithms. Using variance and correlation analysis followed by backward elimination, a subset of relevant features was selected. Recordings were classified into two levels of hoarseness, H<2 and H≥2, yielding a continuous probability score ŷ∈[0,1]. An accuracy of 0.867 and a correlation of 0.805 between the model's predictions and subjective ratings was obtained using only five acoustic features and logistic regression (LR). Further examination of recordings pre- and post-treatment revealed high qualitative agreement with the change in subjectively determined hoarseness levels. Quantitatively, a moderate correlation of 0.567 was obtained. This quantitative approach to hoarseness severity estimation shows promising results and potential for improving the assessment of voice quality.

Efeitos imediatos do inspirômetro de incentivo em mulheres vocalmente saudáveis

ABSTRACT Purpose To evaluate the immediate effect of the incentive spirometer on acoustic measures, aerodynamic measures and on the auditory-perceptual assessment of vocal quality in vocally healthy women. Methods This is an experimental intra-subject comparison study with the participation of 22 women without vocal complaints. Acoustic measures, aerodynamic measures and auditory-perceptual assessment of vocal quality were obtained before and immediately after using the incentive spirometer by the participants. The device was used in the orthostatic position and the participants performed three sets of ten repetitions with a one-minute interval between sets. Results After using the incentive spirometer, there was a significant reduction in jitter, shimmer and PPQ (period perturbation quotient) measurements and an increase in maximum expiratory volume, while the other acoustic and aerodynamic measurements were not significantly impacted. In addition, there was improvement in vocal quality in eight (36.4%) participants and 11 (50.0%) participants showed no changes in the auditory perceptual assessment of voice quality after using the incentive spirometer. Conclusion The use of the incentive spirometer is safe and, in its immediate effect, positively impacts the acoustic measures of short-term aperiodicity of frequency and intensity and increases the maximum expiratory volume in women with healthy voices.

Characterizing Dysphonia After Pediatric Open Airway Reconstruction: Systematic Review and Meta-Analysis.

Pediatric laryngotracheal stenosis often requires open airway reconstruction. While these surgeries establish an airway for adequate ventilation, many patients develop subsequent dysphonia. Numerous studies have reported outcomes related to voice. This study aims to evaluate dysphonia in pediatric patients following open airway reconstruction, focusing on acoustic parameters, perceptual voice quality, and voice-related quality of life. A comprehensive search using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines across 6 databases identified articles involving pediatric patients who underwent open airway reconstruction and reported postoperative vocal acoustic parameters, perceptual voice quality, voice-related quality of life, or vocal mechanics. Articles were assessed for bias risk, and common outcomes were synthesized qualitatively and quantitatively using meta-analyses. Among 4089 articles, 21 were included, involving 497 pediatric patients. Laryngotracheoplasty was the most common procedure followed by cricotracheal resection. The Consensus Auditory-Perceptual Evaluation of Voice (CAPE-V) scale was frequently used to assess voice quality, with a mean score of 55.6 [95% confidence intervals (CIs): 47.9-63.3]. Voice-related quality of life was measured using the pediatric Voice Handicap Index (pVHI) and Pediatric Voice-Related Quality of Life Survey, with mean scores of 35.6 (95% CI: 21.4-49.7) and 83.7 (95% CI: 74.1-93.2), respectively. The fundamental frequency was 210.5 (95% CI: 174.6-246.3). Other common findings included supraglottic phonation, anterior commissure blunting, posterior glottic diastasis, and abnormal vocal cord mobility. Pediatric patients experiencing dysphonia after open airway reconstruction exhibited moderately decreased voice quality and reduced voice-related quality of life. However, there was inconsistency in study protocols and outcome measures used. Preserving voice quality during airway reconstruction is crucial to avoid negative impacts on quality of life.

Clinical Utility and Validation of the Acoustic Voice Quality and Acoustic Breathiness Indexes for Voice Disorder Assessment in English Speakers.

While several acoustic voice metrics are available for clinical voice assessment, there remains a significant need for reliable and ecologically valid tools. The Acoustic Voice Quality Index version 03.01 (AVQI-3) and Acoustic Breathiness Index (ABI) hold potential due to their comprehensive assessment approach, incorporating diverse voice aspects. However, these tools still need to be validated in English-speaking populations. This study assessed the discriminatory accuracy and validity of AVQI-3 and ABI in 197 participants, including 148 with voice disorders. Voice samples were collected, followed by AVQI-3 and ABI calculations. Additionally, auditory-perceptual assessments were conducted by a panel of speech-language pathologists. AVQI-3 and ABI effectively identified disordered voice quality, evidenced by high accuracy (AUCs: 0.84, 0.89), sensitivity, and specificity (thresholds: AVQI-3 = 1.17, ABI = 2.35). Strong positive correlations were observed with subjective voice quality assessments (rs = 0.72, rs = 0.77, p < 0.001). The study highlights AVQI-3 and ABI as promising instruments for clinically assessing voice disorders in U.S. English speakers, underscoring their utility in clinical practice and voice research.

Multidimentional assessment of voice quality in patients with laryngopharyngeal reflux disease.

&lt;b&gt;&lt;br&gt;Introduction:&lt;/b&gt; Gastroesophageal Reflux Disease (GERD) is a common disorder in world population. As a result of the regurgitation of acid content from the stomach to laryngopharynx and larynx, secondary damage of laryngeal mucosa occur, which is highly sensitive to hydrochloric acid, and morphological changes are observed. Symptomatology of laryngopharyngeal reflux is varied which makes differential diagnosis difficult.&lt;/br&gt; &lt;b&gt;&lt;br&gt;Aim:&lt;/b&gt; The aim of the study was the assessment of voice quality, morphological changes in larynx as well as etiology of Laryngopharyngeal Reflux Disease.&lt;/br&gt; &lt;b&gt;&lt;br&gt;Material and method:&lt;/b&gt; The severity of dysphonia was classified using perceptual and acoustic methods as well as RSI. Morphological control was performed using HSDI technique and RFS. Etiological factors were examined basing on barofunction of upper esophageal sphincter and 24-hour pH-metry of air exhaled expressed in Ryan score.&lt;/br&gt; &lt;b&gt;&lt;br&gt;Results:&lt;/b&gt; In the majority of patients with Laryngopharyngeal Reflux, dysphonia was recognized, intensified especially in women (G3R2B0A0S3), which was confirmed in Yanagihara classification (type III) and parameters of acoustic analysis. Voice disorders were the most frequently the result of edema and congestion of interarytenoid area, aytenoids and vocal folds. Those symptoms were caused by the decrease of upper esophageal sphincter tension and acidity of exhaled air which was confirmed in 24-hour pHmetry.&lt;/br&gt; &lt;b&gt;&lt;br&gt;Conclusions:&lt;/b&gt; It is important to educate physicians and patients about the possibilty of negative impact of reflux disease on the occurrence of voice quality disorders. Current diagnostic methods for dysphonia guarantee accurate recognition and therapeutic success improving the prognoses of patients with Laryngopharyngeal Reflux.&lt;/br&gt.

Voice Quality Monitoring in Dementia Households

AbstractBackgroundVoice disorders are common in People Living with Dementia (PLwD) and a decrease in voice quality can be an indicator of cognitive deterioration. Previous computational works have successfully employed voice to detect or predict dementia. Voice quality can be assessed by a speech therapist, or computationally when subjects periodically repeat the same sentences. There is, however, to our knowledge, no research on monitoring voice to track dementia progress from unconstrained data collected in the wild.MethodIn this work, we employ a dataset containing audio recordings of 14 households (a carer, a PLwD and visitors) interacting with Alexa. We identify several voice features, such as speech rate and OpenSmile features that differ between healthy users and PLwD. We create a voice footprint for each PLwD using a Gaussian distribution and identify audio recordings that significantly differ from this baseline over time by combining Expectation‐Minimisation and Mahalanolis distance outliers detection.ResultThe voice features selected are significantly different between our two user groups (p‐value &lt; 0.0001). Training a classifier on those features, allows us to identify healthy subjects and PLwD with over 90% accuracy. We are also able to quality how much the voice differs from its baseline over time.ConclusionWhile we can computationally identify voice variations that are out the ordinary, in the future, we will compare our results to a clinical assessment of voice quality. We will also integrate a semantics analysis to identify grammar errors or the use of wrong words. This will allow us to design an objective index measure for monitoring of speech quality.

ChatGPT performance in laryngology and head and neck surgery: a clinical case-series.

To study the performance of ChatGPT in the management of laryngology and head and neck (LHN) cases. History and clinical examination of patients consulting at the Otolaryngology-Head and Neck Surgery department were presented to ChatGPT, which was interrogated for differential diagnosis, management, and treatment. The ChatGPT performance was assessed by two blinded board-certified otolaryngologists using the following items of a composite score and the Ottawa Clinic Assessment Tool: differential diagnosis; additional examination; and treatment options. The complexity of clinical cases was evaluated with the Amsterdam Clinical Challenge Scale test. Forty clinical cases were submitted to ChatGPT, accounting for 14 (35%), 12 (30%), and 14 (35%) easy, moderate and difficult cases, respectively. ChatGPT indicated a significant higher number of additional examinations compared to practitioners (p = 0.001). There was a significant agreement between practitioners and ChatGPT for the indication of some common examinations (audiometry, ultrasonography, biopsy, gastrointestinal endoscopy or videofluoroscopy). ChatGPT never indicated some important additional examinations (PET-CT, voice quality assessment, or impedance-pH monitoring). ChatGPT reported highest performance in the proposition of the primary (90%) or the most plausible differential diagnoses (65%), and the therapeutic options (60-68%). The ChatGPT performance in the indication of additional examinations was lowest. ChatGPT is a promising adjunctive tool in LHN practice, providing extensive documentation about disease-related additional examinations, differential diagnoses, and treatments. The ChatGPT is more efficient in diagnosis and treatment, rather than in the selection of the most adequate additional examination.

Consensus for voice quality assessment in clinical practice: guidelines of the European Laryngological Society and Union of the European Phoniatricians.

To update the European guidelines for the assessment of voice quality (VQ) in clinical practice. Nineteen laryngologists-phoniatricians of the European Laryngological Society (ELS) and the Union of the European Phoniatricians (UEP) participated to a modified Delphi process to propose statements about subjective and objective VQ assessments. Two anonymized voting rounds determined a consensus statement to be acceptable when 80% of experts agreed with a rating of at least 3/4. The statements with ≥ 3/4 score by 60-80% of experts were improved and resubmitted to voting until they were validated or rejected. Of the 90 initial statements, 51 were validated after two voting rounds. A multidimensional set of minimal VQ evaluations was proposed and included: baseline VQ anamnesis (e.g., allergy, medical and surgical history, medication, addiction, singing practice, job, and posture), videolaryngostroboscopy (mucosal wave symmetry, amplitude, morphology, and movements), patient-reported VQ assessment (30- or 10-voice handicap index), perception (Grade, Roughness, Breathiness, Asthenia, and Strain), aerodynamics (maximum phonation time), acoustics (Mean F0, Jitter, Shimmer, and noise-to-harmonic ratio), and clinical instruments associated with voice comorbidities (reflux symptom score, reflux sign assessment, eating-assessment tool-10, and dysphagia handicap index). For perception, aerodynamics and acoustics, experts provided guidelines for the methods of measurement. Some additional VQ evaluations are proposed for voice professionals or patients with some laryngeal diseases. The ELS-UEP consensus for VQ assessment provides clinical statements for the baseline and pre- to post-treatment evaluations of VQ and to improve collaborative research by adopting common and validated VQ evaluation approach.

Test-Retest Reliability of the Acoustic Voice Quality Index and the Acoustic Breathiness Index

The acoustic voice quality index (AVQI) and the acoustic breathiness index (ABI) are two validated measurements for the objective-acoustic assessment of voice quality. The aim of this study was to evaluate the relative and absolute reliability of AVQI and ABI as well as detect the natural variability of vocally-healthy voices. Totally, 39 vocally-healthy participants received weekly an AVQI- and ABI measurement using the freeware VOXplot over a period of 3 weeks. This study is a within-subject design to assess significant differences between the test and retest measurements (test and mean of two retests) of AVQI and ABI with the paired sample t test and to investigate the reliability of these two acoustic parameters with the intraclass correlation coefficient (ICC), Bland-Altman plot, and the minimal detectable change (MDC). No significant differences between the test-retest measurements of AVQI and ABI were revealed (all P-values>0.05). The relative reliability of AVQI and ABI showed good results (eg, ICC=0.81, and ICC=0.92, respectively). Absolute reliability measured with the MDC yielded a test-retest value of 0.78 and 0.66 for the AVQI and ABI, respectively. Deviations within this range may be due to natural variations of the voice (random bias). AVQI and ABI revealed high-reliability results in a test-retest measurement of vocally-healthy participants.

Acoustic Parameters in the Evaluation of Voice Quality of Choral Singers. Prototype of Mobile Application for Voice Quality Evaluation

Choral singers are among intensive voice users whose excessive vocal effort puts them at risk of developing voice disorders. The aim of the work was to assess voice quality for choral singers in the choir at the Polish-Japanese Academy of Information Technology. This evaluation was carried out using the acoustic parameters from the COVAREP (A Collaborative Voice Analysis Repository For Speech Technologies) repository. A prototype of a mobile application was also prepared to allow the calculation of these parameters. The study group comprised 6 male and 19 female choir singers. The control group consisted of healthy non-singing individuals, 50 men and 39 women. Auditory perceptual assessment (using the RBH scale) as well as acoustic analysis were used to test the voice quality of all the participants. The voice quality of the female choir singers proved to be normal in comparison with the control group. The male choir singers were found to have tense voice in comparison with the controls. The parameters which proved most effective for voice evaluation were Peak Slope and Normalized Amplitude Quotient.