Logopedics Phoniatrics Vocology最新文献

The effectiveness of voice hygiene and practical training for preschool teachers in Bosnia and Herzegovina. “波斯尼亚和黑塞哥维那学前教师语音卫生和实践培训的有效性”。

IF 0.7 4区医学

Logopedics Phoniatrics Vocology Pub Date : 2026-04-01 Epub Date: 2025-09-17 DOI: 10.1080/14015439.2025.2560967

Amela Ibrahimagić, Ana Bonetti, Sujata Maya Huestegge

{"title":"The effectiveness of voice hygiene and practical training for preschool teachers in Bosnia and Herzegovina.","authors":"Amela Ibrahimagić, Ana Bonetti, Sujata Maya Huestegge","doi":"10.1080/14015439.2025.2560967","DOIUrl":"10.1080/14015439.2025.2560967","url":null,"abstract":"Effective voice education promotes healthy voice use, particularly for kindergarten teachers in demanding environments. This study assessed the effectiveness of a brief, workplace-based voice education program for the preschool teachers. Teachers were quasi-randomly assigned based on work schedules to either the Direct Voice Training Group (N = 31), which received a four-hour face-to-face training session and an educational booklet, or the Educational Booklet Only Group (N = 45). Outcomes were measured using the Vocal Fatigue Index (VFI) and blinded perceptual voice quality assessments via the GRBAS scale at baseline and three months post-intervention. Nonparametric Wilcoxon signed-rank tests assessed statistical significance, with effect sizes (r) calculated. Both groups improved significantly, but the Direct Voice Training Group showed broader improvements, with small to medium effect sizes (r = 0.25-0.38), whereas the Booklet Only Group had limited improvements (r < 0.3). Blinded evaluations confirmed greater benefits for the direct training group. These findings highlight the value of brief, targeted interventions for occupational vocal health, though small to medium effect sizes suggest that more intensive interventions may be required for clinically significant outcomes.","PeriodicalId":49903,"journal":{"name":"Logopedics Phoniatrics Vocology","volume":" ","pages":"51-59"},"PeriodicalIF":0.7,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145081974","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The perception of voice handicap in singers: its relationship with perfectionism and perceived stress. 歌手对嗓音障碍的感知：与完美主义和感知压力的关系

IF 0.7 4区医学

Logopedics Phoniatrics Vocology Pub Date : 2026-04-01 Epub Date: 2025-04-07 DOI: 10.1080/14015439.2025.2487441

Laura González-Sanvisens, Cecília Gassull, Josep Vila-Rovira, Mariangeles Arévalo

{"title":"The perception of voice handicap in singers: its relationship with perfectionism and perceived stress.","authors":"Laura González-Sanvisens, Cecília Gassull, Josep Vila-Rovira, Mariangeles Arévalo","doi":"10.1080/14015439.2025.2487441","DOIUrl":"10.1080/14015439.2025.2487441","url":null,"abstract":"Introduction: Research indicates that psychological factors such as stress and perfectionism play a crucial role in voice problems, either triggering them or intensifying the perception of difficulty. This study examines the relationship between voice handicap, perceived stress, and perfectionism in singers, exploring the impact of factors such as vocal role (soloists, choral singers, and students), music genre, years of professional experience, and the correlation between performance competency perception, perceived stress, and perfectionism.Method: 155 singers (choral singers, soloists, and students) were assessed using the Multidimensional Perfectionism Scale (MPS), the Perceived Stress Scale (PSS-10), and the Singing Voice Handicap Index-10 (SVHI-10), along with an ad hoc questionnaire exploring their perception of performance in the work context.Results: Correlations were found between SVHI-10, PSS-10, and MPS, although the behavior varied depending on vocal role (p < .01) and years of professional experience (p < .01), except for perceived stress (p = .07). Among the MPS subscales, \"Fear of mistakes\" and \"Expectations of success\" showed stronger correlations with SVHI-10 (p < .01) compared to the other subscales. Singers who experienced their performance more negatively than positively in the work context had higher scores on all three scales.Conclusions: This study explored the complex relationship between voice handicap, perceived stress, and perfectionism in singers, revealing role-based differences. Students displayed the highest scores across all scales, in contrast with experienced singers who had lower scores. These findings emphasize the need to address psychological factors in vocal training and support programs.","PeriodicalId":49903,"journal":{"name":"Logopedics Phoniatrics Vocology","volume":" ","pages":"1-9"},"PeriodicalIF":0.7,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143796849","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Why do teachers with voice disorders keep teaching? Insights from applications of social capital motives. 为什么有声音障碍的教师会继续教学？来自社会资本动机应用的洞见。

IF 0.7 4区医学

Logopedics Phoniatrics Vocology Pub Date : 2026-04-01 Epub Date: 2025-07-01 DOI: 10.1080/14015439.2025.2523738

Lady Catherine Cantor-Cutiva, Lindon J Robison, Eric J Hunter

{"title":"Why do teachers with voice disorders keep teaching? Insights from applications of social capital motives.","authors":"Lady Catherine Cantor-Cutiva, Lindon J Robison, Eric J Hunter","doi":"10.1080/14015439.2025.2523738","DOIUrl":"10.1080/14015439.2025.2523738","url":null,"abstract":"Introduction: This study investigated why teachers with voice disorders continue teaching by surveying their motives described in social capital theory.Methods: Teachers were asked to rate their motives for continued teaching even with voice disorders using online surveys. The five key motives (social capital framework) were: Motive #1 (selfishness), Motive #2 (internal validation), Motive #3 (external validation), Motive #4 (transcendence or altruism), and Motive #5 (belonging).Results: As teachers' income increased, so did the relative importance of the transcendence motive. Income maintenance (selfishness) accounted for 47% of the total motivation, with teachers with a master's degree and higher incomes being less likely to prioritize this motive. Teachers reporting bad voice quality were more likely to prioritize income (selfishness) and less likely to be motivated by helping others (altruism) or feel connected to other people (belonging).Conclusion: Voice problems can negatively impact a teacher's sense of fulfilment and motivation beyond financial constraints. These findings highlight the need for implementing preventive measures for voice disorders in schools that can address voice problems before they significantly affect teachers' performance and students' learning. Moreover, competitive teacher salaries and benefits may create a supportive environment where educators feel empowered to focus on their students' needs.","PeriodicalId":49903,"journal":{"name":"Logopedics Phoniatrics Vocology","volume":" ","pages":"10-18"},"PeriodicalIF":0.7,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12342425/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144545841","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Embracing variability: toward proactive and precision-based voice science. 拥抱可变性：走向主动和精确的语音科学。

IF 0.7 4区医学

Logopedics Phoniatrics Vocology Pub Date : 2026-04-01 Epub Date: 2025-09-25 DOI: 10.1080/14015439.2025.2562929

Eric J Hunter, Mark L Berardi

{"title":"Embracing variability: toward proactive and precision-based voice science.","authors":"Eric J Hunter, Mark L Berardi","doi":"10.1080/14015439.2025.2562929","DOIUrl":"10.1080/14015439.2025.2562929","url":null,"abstract":"Purpose: We propose that rigorous measurement practices combined with frameworks focused on functional capacity can transform physiological variability, traditionally dismissed as \"noise,\" into diagnostic information for precision-based voice care. A conceptual framework integrating vocal capacity, demand response, reserve, and recovery enables individualized monitoring, predictive risk assessment, and proactive intervention, mirroring progress in cardiology and orthopedics where variability became diagnostic. Applied to voice, this approach can transform clinical practice: a teacher's inconsistent perturbation may signal depleted reserve requiring pacing; a singer's instability may reflect insufficient reserve under rehearsal load, guiding recovery scheduling; and a neurological patient's fluctuations may indicate variable demand response, informing targeted intervention.Conclusions: Variability-informed models can establish individual baselines, track change trajectories, and identify functional thresholds before overt disorder emerges. Embracing physiological variability offers a path to align clinical strategies with functional sustainability, transforming uncertainty into actionable insight for research and clinical practice.","PeriodicalId":49903,"journal":{"name":"Logopedics Phoniatrics Vocology","volume":" ","pages":"60-68"},"PeriodicalIF":0.7,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12884546/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145151759","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Biomechanical insights into intrinsic laryngeal control: a cross-linguistic study of Mandarin vowel production in native Mandarin speakers and South Korean learners. 喉内控制的生物力学见解：母语为普通话的人和韩国学习者普通话元音产生的跨语言研究。

IF 0.7 4区医学

Logopedics Phoniatrics Vocology Pub Date : 2026-04-01 Epub Date: 2025-09-15 DOI: 10.1080/14015439.2025.2556766

Mingjun Ji, Jinwei Lan, Jianhan Lei, Can Zhang, Boquan Liu

{"title":"Biomechanical insights into intrinsic laryngeal control: a cross-linguistic study of Mandarin vowel production in native Mandarin speakers and South Korean learners.","authors":"Mingjun Ji, Jinwei Lan, Jianhan Lei, Can Zhang, Boquan Liu","doi":"10.1080/14015439.2025.2556766","DOIUrl":"10.1080/14015439.2025.2556766","url":null,"abstract":"Purpose: This study examines differences in intrinsic laryngeal muscle control during Mandarin vowel production between native Mandarin speakers and advanced South Korean learners. By analyzing vocal fold vibrations and muscle activation patterns, it provides a biomechanical perspective on second language phonetic challenges.Method: Twenty native Mandarin speakers (control) and twenty advanced South Korean learners (experimental), all from the same university, participated in the study. Participants produced monosyllabic words while formant frequencies were recorded. A computational vocal fold-airway model simulated vowel production, focusing on the activation of the cricothyroid (CT), thyroarytenoid (TA), and lateral cricoarytenoid (LC) muscles. Simulated formant frequencies were compared with actual recordings to identify muscle control differences.Results: Native speakers exhibited higher CT and TA activation for /a/ and /i/, while South Korean learners showed reduced activation of these muscles and increased reliance on the LC muscle. For /u/, the native speakers' model revealed lower overall muscle activation, whereas learners over-activated all three muscles.Conclusions: The findings reveal distinct laryngeal control patterns between native and non-native speakers, emphasizing the role of biomechanical modeling in second language phonetics research. By identifying specific muscle activation differences, this study provides insights into the physiological basis of vowel articulation challenges and lays the groundwork for future research on cross-linguistic phonetic and phonemic acquisition.","PeriodicalId":49903,"journal":{"name":"Logopedics Phoniatrics Vocology","volume":" ","pages":"29-50"},"PeriodicalIF":0.7,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145066171","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Comparison of olfactory functions of individuals with total laryngectomy using different voice restoration methods. 不同声音恢复方法对全喉切除术患者嗅觉功能的影响。

IF 0.7 4区医学

Logopedics Phoniatrics Vocology Pub Date : 2026-04-01 Epub Date: 2025-10-17 DOI: 10.1080/14015439.2025.2574617

Rıdvan Başaran, Fatma Esen Aydınlı, Önal İncebay, Nilda Sütay Süslü

{"title":"Comparison of olfactory functions of individuals with total laryngectomy using different voice restoration methods.","authors":"Rıdvan Başaran, Fatma Esen Aydınlı, Önal İncebay, Nilda Sütay Süslü","doi":"10.1080/14015439.2025.2574617","DOIUrl":"10.1080/14015439.2025.2574617","url":null,"abstract":"Purpose: To investigate whether there is a difference in olfactory functions among individuals who use different voice restoration methods after total laryngectomy.Method: The study group for this research comprised individuals who had undergone total laryngectomy and aged 44 to 75 years; 10 participants using oesophageal speech, 10 participants using tracheoesophageal speech, and 10 participants using electrolarynx were included. The control group comprised 10 individuals with normal olfactory function of similar age and gender to the individuals in the study group. The participants' olfactory functions were evaluated using the Sniffin Sticks Extended Test. European Organisation for Research and Treatment of Cancer Quality of Life Questionnaire - H&N-35 was used as a subjective scale.Result: All laryngectomised patients exhibited olfactory impairment, with 73.3% diagnosed with anosmia and 26.7% with hyposmia. Regarding Sniffin Sticks Test combined scores; the mean values of voice prosthesis users, electrolarynx and oesophageal speech group were 8.4, 10.1 and 21.6 respectively, while in the control group it was 38.2. In terms of Sniffin Sticks Test composite scores, the oesophageal speech group had significantly higher scores than the voice prosthesis and electrolarynx groups (p < 0.001).Conclusion: While all laryngectomised patients showed olfactory dysfunction, those using oesophageal speech - a somewhat overlooked rehabilitation method - exhibited statistically significant preservation of olfactory function compared to other voice restoration techniques. These findings suggest that oesophageal speech may offer distinct advantages for maintaining post-laryngectomy olfactory capacity, warranting further consideration in clinical practise.","PeriodicalId":49903,"journal":{"name":"Logopedics Phoniatrics Vocology","volume":" ","pages":"19-28"},"PeriodicalIF":0.7,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145314027","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Embracing a multilingual approach for assessment in multilingual people with aphasia. 采用多语言方法对多语言失语症患者进行评估。

IF 0.7 4区医学

Logopedics Phoniatrics Vocology Pub Date : 2026-03-23 DOI: 10.1080/14015439.2026.2641477

Mira Goral

{"title":"Embracing a multilingual approach for assessment in multilingual people with aphasia.","authors":"Mira Goral","doi":"10.1080/14015439.2026.2641477","DOIUrl":"https://doi.org/10.1080/14015439.2026.2641477","url":null,"abstract":"In this comment, I advocate for embracing a true multilingual approach in the assessment of acquired language difficulties-by allowing people to use their complete linguistic repertoire-rather than the traditional binary approach, which assesses each language separately. I first briefly review the shift that has occurred in the fields of neurolinguistics and psycholinguistics of bilingualism from binary to non-binary views of both the processing of multiple languages in the brain and in the study of multilingual individuals. I then address assessment challenges in multilingual individuals with aphasia and suggest that, when appropriate, multilingual people could be evaluated and treated in a context that allows them to employ their complete linguistic repertoire rather than in a context in which they have to select one target language and inhibit the other(s). This new assessment practice can then alleviate added cognitive and affective demands associated with language selection and inhibition, and can provide ecologically valid information about the communication abilities of the individual. This new approach is suitable for multilingual people who tend to use their multiple languages with their interlocutors, and may be less relevant for those multilingual people who use their languages in a diglossic manner. Customizing services in accordance with multilingualism-related variables may enhance best practices and well-being. allowing people to use their complete linguistic repetoire - in.","PeriodicalId":49903,"journal":{"name":"Logopedics Phoniatrics Vocology","volume":" ","pages":"1-7"},"PeriodicalIF":0.7,"publicationDate":"2026-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147505683","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Speech outcomes in children with cochlear implants: the impact of implantation age on intelligibility, articulation, and phonological skills. 植入人工耳蜗儿童的言语效果：植入年龄对可理解性、发音和语音技能的影响。

IF 0.7 4区医学

Logopedics Phoniatrics Vocology Pub Date : 2026-03-13 DOI: 10.1080/14015439.2026.2642313

Beyza Pehlivan Bozoğlu, Esra Özcebe, Ayşın Noyan Erbaş

{"title":"Speech outcomes in children with cochlear implants: the impact of implantation age on intelligibility, articulation, and phonological skills.","authors":"Beyza Pehlivan Bozoğlu, Esra Özcebe, Ayşın Noyan Erbaş","doi":"10.1080/14015439.2026.2642313","DOIUrl":"10.1080/14015439.2026.2642313","url":null,"abstract":"Background: This study aimed to compare speech intelligibility and articulation-phonological skills of children with congenital severe-to-profound sensorineural hearing loss who received cochlear implantation at one of three implantation-age ranges (12-17, 18-23, and 24-29 months) with those of age-matched peers with typical hearing.Methods: The study included 45 children (32 males and 13 females) who received cochlear implants at 12-17, 18-23, or 24-29 months and were 5-7 years old at data collection. Each implantation-age subgroup consisted of n = 15 children. A control group of 15 children (7 males and 8 females) with typical hearing, aged 5-7, was also included. The Turkish Articulation and Phonology Test (SST) were used to assess articulation and phonological skills. The Intelligibility in Context Scale (ICS) was used to assess speech intelligibility.Results: Children implanted at 12-17 months demonstrated significantly more advanced articulation and phonological skills compared with those implanted at later ages. Nonetheless, even early-implanted children did not attain articulation, phonological skills or speech intelligibility levels observed in age-matched peers with typical hearing.Conclusions: These findings underscore the importance of early cochlear implantation during infancy. While early implantation is associated with improved speech outcomes, children with cochlear implants may continue to exhibit speech sound disorders affecting their articulation, phonological skills, and intelligibility. This suggests a need for ongoing, speech-focused intervention, in addition to general language support, with continuous monitoring and active family involvement.","PeriodicalId":49903,"journal":{"name":"Logopedics Phoniatrics Vocology","volume":" ","pages":"1-12"},"PeriodicalIF":0.7,"publicationDate":"2026-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147445769","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The effect of aging and gender on oral diadochokinetic performance. 年龄和性别对口腔代谢动力学性能的影响。

IF 0.7 4区医学

Logopedics Phoniatrics Vocology Pub Date : 2026-03-11 DOI: 10.1080/14015439.2026.2635712

B V M Mahesh, Devappa Shashank, Narayan Manasa, C D Santosha

{"title":"The effect of aging and gender on oral diadochokinetic performance.","authors":"B V M Mahesh, Devappa Shashank, Narayan Manasa, C D Santosha","doi":"10.1080/14015439.2026.2635712","DOIUrl":"10.1080/14015439.2026.2635712","url":null,"abstract":"Purpose: Aging affects speech motor performance, particularly articulatory skills, often measured through oral diadochokinetic (ODDK) rates. The purpose of this was to examine the effects of age and gender on two tasks, namely alternating and sequential motion rates (SMRs) in healthy elderly Kannada speakers, and compared performances across tasks.Methods: Sixty native Kannada speakers aged 61-80 performed rapid repetition tasks (/pa/, /ta/, /ka/ for alternating motion rate (AMR); /pataka/ for SMR). ODDK rates were recorded and analyzed using the Motor Speech Profile.Results: Age had no significant effect on ODDK rates. However, a significant two-way interaction emerged between the type of task and gender. Subsequent analyses of the interaction effects demonstrated that the SMR was 16.52% and 14.73% faster than the AMRs in males and females, respectively. With regard to gender, the diadochokinetic (DDK) rates of the elderly male participants were significantly higher than those of the female participants for stimuli /pa/ (5.52 syllables/s and 4.90 syllables/s), /ta/ (5.06 syllables/s and 4.22 syllables/s), and /pataka/ (6.17 syllables/s and 5.43 syllables/s), with the exception of the syllable /ka/ (4.86 syllables/s and 4.77 syllables/s).Conclusions: The study findings highlighted that the decline in DDK rates may be language-specific. While disagreeing with some of the recent study findings on age-related decline in DDK rate, current findings underscore the need to use gender-specific reference values while assessing the articulatory motor integrity in the Kannada-speaking elderly population.","PeriodicalId":49903,"journal":{"name":"Logopedics Phoniatrics Vocology","volume":" ","pages":"1-17"},"PeriodicalIF":0.7,"publicationDate":"2026-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147437250","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Automatic assessment of voice quality using machine learning. 使用机器学习的语音质量自动评估。

IF 0.7 4区医学

Logopedics Phoniatrics Vocology Pub Date : 2026-02-25 DOI: 10.1080/14015439.2026.2628250

Yat Chun Au, Nan Yan, Manwa L Ng

{"title":"Automatic assessment of voice quality using machine learning.","authors":"Yat Chun Au, Nan Yan, Manwa L Ng","doi":"10.1080/14015439.2026.2628250","DOIUrl":"https://doi.org/10.1080/14015439.2026.2628250","url":null,"abstract":"Objectives: This study aimed to develop and validate machine learning (ML) models for automated prediction of perceptual dysphonia severity, as indexed by the Grade (G) parameter of the GRBAS scale, using acoustic analyses of sustained vowels. The overarching goal was to enhance objectivity, reproducibility, and efficiency in clinical voice assessment.Methods: A total of 524 sustained/a/samples were collected from three databases. The evaluations of all recordings by ten raters using the GRBAS scale, that achieved excellent interrater reliability (Krippendorff's α = 0.96), were modelled. Forty-seven acoustic features spanning spectral, cepstral, perturbation, and noise-based indices were extracted using Parselmouth (Praat). Five ML classifiers-Decision Tree (DT), Random Forest (RF), Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), and Categorical Boosting (CatBoost)-were trained using 5-fold cross-validation (80/20 split) and evaluated by accuracy, F1-score, and quadratic weighted kappa (QWK).Results: Gradient boosting algorithms outperformed traditional tree-based models. LightGBM achieved the highest QWK (0.945), followed by CatBoost (QWK = 0.941) and XGBoost (QWK = 0.935). Feature-importance analyses identified cepstral measures-particularly Smoothed Cepstral Peak Prominence (CPPS), Cepstral Spectral Index of Dysphonia (CSID), Acoustic Voice Quality Index (AVQI), Harmonics-to-Noise Ratio (HNR) as the most influential predictors of perceptual Grade (G), while jitter and shimmer parameters contributed minimally. Correlation analyses confirmed strong associations between Grade and AVQI (r = 0.854), HNR (r = -0.853), and cepstral indices (r = -0.835 to -0.832).Conclusions: Gradient boosting methods, particularly LightGBM, produced near-expert agreement with perceptual ratings, supporting their potential as objective, interpretable tools for clinical dysphonia assessment.","PeriodicalId":49903,"journal":{"name":"Logopedics Phoniatrics Vocology","volume":" ","pages":"1-18"},"PeriodicalIF":0.7,"publicationDate":"2026-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147285729","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0