检索结果-内蒙古大学图书馆

Accuracy and Cut-Off Values of Cepstral Measures in the Clinical Evaluation of Brazilian Portuguese Speakers

Journal of Voice 2024年

作者： Lopes, Leonardo Wanderley de Abreu, Samuel Ribeiro Communication Science Disorders Department Graduate Program in Decision Models and Health Universidade Federal da Paraíba – UFPB PB João Pessoa Brazil Graduate Program in Decision Models and Health Universidade Federal da Paraíba – UFPB PB João Pessoa Brazil

Objective: To identify the accuracy and cut-off values of the cepstral peak prominence (CPP) and cepstral peak prominence-smoothed (CPPS) obtained from different speech tasks, to identify dysphonic voices in Brazilian Portuguese speakers, and to verify the correlation between these measures and the overall severity of dysphonia (OS). Method: In a study with 376 subjects—277 with dysphonia and 99 controls—we recorded four speech tasks and assessed OS with a visual analog scale. We extracted CPP and CPPS from these recordings and analyzed them using receiver operating characteristic curves to determine cut-off values and other performance metrics (area under curve, accuracy, sensitivity, specificity, predictive values, and likelihood ratios). Results: CPP values below 28.15 dB (sustained vowel [Ɛ]), 28.77 dB (sustained vowel [a]), 28.58 dB (all Consensus Auditory-Perceptual Evaluation of Voice (CAPE-V) sentences), and CPPS values below 16.42 dB (sustained vowel [Ɛ]), 17.02 dB (sustained vowel [a]), and 11.30 dB (all CAPE-V sentences) are indicative of the presence of dysphonia. CPP_VE, CPP_VA, CPP_CAPE-V, CPP_VS, CPPS_VE, CPPS_VA, CPPS_Count, CPPS_CAPE-V e CPPS_VS, and CPPS_VS can explain the variability of OS from 19% to 57.9%. Conclusions: The cut-off values for CPP_VE, CPP_VA, CPP_CAPE-V, CPPS_VE, CPPS_CAPE-V, and CPPS_VA obtained from Praat software can be used as a reference for the clinical voice assessment of Brazilian Portuguese speakers in the respective speech tasks. Analysis of the correlation coefficients of the cepstral measures investigated provided us with a predictive model of OS perception based on each measure/speech task. © 2024 The Voice Foundation

关键词： Accuracy diagnostic Acoustic Cepstral measures Dysphonia Voice disorders

来源：评论

学校读者我要写书评

暂无评论

Different Performances of Machine Learning models to Classify Dysphonic and Non-Dysphonic Voices

引用

Journal of Voice 2025年第3期39卷 577-590页

作者： Leite, Danilo Rangel Arruda de Moraes, Ronei Marcos Lopes, Leonardo Wanderley Department of Statistics Graduate Program in Health Decision Models Universidade Federal da Paraíba – UFPB Paraíba João Pessoa Brazil Brazilian Hospital Services Company- Ebserh Universidade Federal da Paraíba – UFPB Paraíba João Pessoa Brazil Department of Statistics Universidade Federal da Paraíba – UFPB Paraíba João Pessoa Brazil Department of Speech-Language and Hearing Sciences Graduate Program in Linguistics Universidade Federal da Paraíba – UFPB Paraíba João Pessoa Brazil

Objective: To analyze the performance of 10 different machine learning (ML) classifiers for discrimination between dysphonic and non-dysphonic voices, using a variance threshold as a method for the selection and reduction of acoustic measurements used in the classifier. Method: We analyzed 435 samples of individuals (337 female and 98 male), with a mean age of 41.07 ± 13.73 years, of which 384 were dysphonic and 51 were non-dysphonic. From the sustained /ε/ vowel sample, 34 acoustic measurements were extracted, including traditional perturbation and noise measurements, cepstral/spectral measurements, and measurements based on nonlinear models. The variance method was used to select the best set of acoustic measurements. We tested the performance of the best-selected set with 10 ML classifiers using precision, sensitivity, specificity, accuracy, and F1-Score measurements. The kappa coefficient was used to verify the reproducibility between the two datasets (training and testing). Results: The naive Bayes (NB) and stochastic gradient descent classifier (SGDC) models performed best in terms of accuracy, AUC, sensitivity, and specificity for a reduced dataset of 15 acoustic measures compared to the full dataset of 34 acoustic measures. SGDC and NB obtained the best performance results, with an accuracy of 0.91 and 0.76, respectively. These two classifiers presented moderate agreement, with a Kappa of 0.57 (SGDC) and 0.45 (NB). Conclusion: Among the tested models, the NB and SGDC models performed better in discriminating between dysphonic and non-dysphonic voices from a set of 15 acoustic measures. © 2022 The Voice Foundation

关键词： Acoustic Artificial intelligence Machine learning Voice Voice disorders

来源：评论

学校读者我要写书评

暂无评论

Integrated Vocal Deviation Index (IVDI): A Machine Learning Model to Classifier of the General Grade of Vocal Deviation

引用

Journal of Voice 2024年

作者： Lima-Filho, Luiz Medeiros Araujo Lopes, Leonardo Wanderley Filho, Telmo de Menezes e Silva Department of Statistics Member of the Graduate Program in Decision Models and Health Universidade Federal da Paraíba - UFPB Paraíba João Pessoa Brazil Department of Communication Science Disorders Member of the Graduate Program in Decision Models and Health Universidade Federal da Paraíba - UFPB Paraíba João Pessoa Brazil School of Engineering Mathematics and Technology University of Bristol Bristol United Kingdom

Objective: To develop a multiparametric index based on machine learning (ML) to predict and classify the overall degree of vocal deviation (GG). Method: The sample consisted of 300 dysphonic and non-dysphonic participants of both sexes. Two speech tasks were sustained vowel [a] and connected speech (counting numbers from 1 to 10). Five speech-language pathologists performed the auditory-perceptual judgment (APJ) of the GG and the degrees of roughness (GR), breathiness (GB), instability (GI), and strain (GS). We extracted 47 acoustic measurements from these tasks. The APJ result and the acoustic measurements were used to develop the multiparametric index. We used mean absolute error, root mean square error, and coefficient of determination (R²) to select the best model of ML to predict GG and feature importance to select the best set of variables for the index. After classifying the GG between nondysphonic, mild, moderate, and severe, the final model was validated using accuracy, sensitivity, specificity, predictive values, likelihood ratios, F1-Score, and weighted kappa. Results: The gradient boost model showed the best performance among the ML models. Eight features were selected in the model, including four acoustic measures (jitterLoc, smoothed cepstral peak prominenc, mean harmonic-to-noise ratio (HNRmean), and correlation) and four APJ measures (GR, GB, GS, and GI). The final model correctly classified 93.75% of participants and obtained a weighted kappa index of 0.9374, demonstrating the model's excellent performance. Conclusion: The Integrated Vocal Deviation Index includes four acoustic measures and four auditory-perceptual measures and showed excellent performance in classifying voices according to GG. © 2024 The Voice Foundation

关键词： Machine learning—Acoustic—Voice disorders—Dysphonia—Automatic diagnosis.

来源：评论

学校读者我要写书评

暂无评论

Occurrence of Auditory Impairments in Individuals With Dysphonia: A Scoping Review

引用

Journal of Voice 2024年

作者： de Paiva, Maxsuel Alves Avelino de Araújo Lima-Filho, Luiz de Medeiros da Silva, Francisco Tiago Meireles Lopes, Leonardo Wanderley Speech-Language Pathologist Ph.D. Student of the Graduate Program in Decision Models and Health Universidade Federal da Paraíba - UFPB João Pessoa Brazil Statistician Associate Professor at the Department of Statistics Member of the Graduate Program in Decision Models and Health Universidade Federal da Paraíba - UFPB João Pessoa Brazil Speech-Language Pathologist Ph.D. Student of the Graduate Program in Linguistics Universidade Federal da Paraíba - UFPB João Pessoa Brazil Speech-Language Pathologist Full Professor at the Department of Communication Science Disorders Member of the Graduate Program in Decision Models and Health Universidade Federal da Paraíba - UFPB João Pessoa Brazil

Aim: To investigate the occurrence of auditory impairments in individuals with dysphonia and to describe the results of behavioral and electrophysiological audiological assessments in this population. Study Design: A scoping review. Method: A scoping review following the guidelines of the Joanna Briggs Institute Manual for Evidence Synthesis for Scoping Reviews and PRISMA-ScR. A search was carried out using the electronic databases PubMed, Scielo, and Lilacs, as well as the gray literature via Google Scholar. Using the Rayyan platform, the selection and extraction of data from the studies was carried out independently and blindly by two reviewers, with excellent agreement. The studies included in the review were subjected to extraction of the following information for analysis: authors, year of publication, objective, sample characteristics, dysphonia classification, audiological assessment procedure, and conclusion. Results: About 100 studies were found, and 13 eligible studies were included in the analysis. Of the studies included, 92.3% (n = 12) adopted cross-sectional designs, 76.9% (n = 10) investigated auditory functions in individuals with behavioral dysphonia, and 23.1% (n = 3) with organic dysphonia. The samples consisted of children in 53.8% (n = 7) of the studies and adults in 46.2% (n = 6), both with dysphonia. Around 53.80% (n = 7) of the studies included control groups without dysphonia. As for audiological assessment methods, 53.8% (n = 7) used behavioral tests of central auditory processing, 15.4% (n = 2) electrophysiological assessment, and 30.8% (n = 4) a combination of both. Conclusion–: Individuals with dysphonia, especially of the behavioral type, may have deficits in auditory function. The main impairments refer to central auditory processing, especially in skills involving temporal processing, figure-ground skills, and auditory closure. Electrophysiological assessment does not show any significant differences between individuals with and witho

关键词： Dysphonia—Voice disorders—Hearing disorders—Hearing tests.

来源：评论

学校读者我要写书评

暂无评论

Effectiveness of Temporal Auditory Skills Training Associated With Conventional Auditory Training in the Auditory-Perceptual Judgment of Voice: Preliminary Data

引用

Journal of Voice 2024年

作者： da Silva Paz, Karoline Evangelista de Moraes, Ronei Marcos Gielow, Ingrid da Silva, Allan Carlos França Almeida, Anna Alice Lopes, Leonardo Wanderley Graduate Program in Decision Models and Health Universidade Federal da Paraíba - UFPB PB João Pessoa Brazil Fundação Getúlio Vargas - FGV SP São Paulo Brazil

Objective: To verify whether there are differences in the performance and reliability of speech-language-hearing students between the moments of auditory-perceptual judgment (APJ) of voice before and after temporal auditory skills training and conventional auditory-perceptual training (APT). Methods: Both trainings were applied to 30 speech-language pathology students, with the following stages: 1—Initial APJ of the general grade (GG), breathiness (GB), and roughness (GR) with 30 samples of the sustained vowel [Ɛ], plus 20% of repetitions (six samples), analyzed with a visual analog scale;2—Temporal auditory skills training on the online platform Afinando o Cérebro, with a total duration of 4 hours;3—APJ of GG, GR, and GB after training in Afinando o Cérebro;4—APT in the classroom with a total duration of 6 hours;5—APJ of GG, GR, and GB after APT. Results: There was a significant difference in the students' performance in the APJ of GG after the training. The agreement in identifying voices as dysphonic or nondysphonic increased after each training. Conclusion: Temporal auditory skills training associated with APT has the potential to improve the performance of speech-language-hearing students in APJ of voice, especially in GG. © 2024 The Voice Foundation

关键词： Auditory training Auditory-perceptual judgment Dysphonia Voice Voice quality

来源：评论

学校读者我要写书评

暂无评论

Examining the Perception of Vocal Deviation by Dysphonic and Nondysphonic Women

引用

Journal of Voice 2025年

作者： França, Fernanda Pereira de Almeida, Anna Alice Figueiredo da Silva Paz, Karoline Evangelista Constantini, Ana Carolina Odagma, Rosiane Kimiko Yamasaki Alves, Giorvan Anderson dos Santos Lopes, e Leonardo Wanderley Linguistics from the Graduate Program in Linguistics at the Federal University of Paraíba Paraíba João Pessoa Brazil Department of Speech-Language Pathology at the Federal University of Paraíba Paraíba João Pessoa Brazil Health Decision Models from the Graduate Program in Health Decision Models at the Federal University of Paraíba Paraíba João Pessoa Brazil Department of Human Development and Rehabilitation at the State University of Campinas São Paulo Campinas Brazil Department of Speech Therapy at the Federal University of São Paulo São Paulo São Paulo Brazil

Aim: To investigate the auditory perception of vocal deviation by dysphonic and nondysphonic women and to correlate the accuracy rate with acoustic measurements. Methods: In total, 24 dysphonic women allocated to an experimental group (EG) and 10 nondysphonic women allocated to the control group (CG) participated in this study. The volunteers filled in the vocal screening form the vocal symptom scale (VoiSS) self-assessment protocol and made voice recordings during the emission of the vowel /Ɛ/, whose degree of deviation was examined through perceptual-auditory and acoustic evaluation;all the participants underwent audiometry. Three experiments were conducted for the perception tests. The first experiment consisted of randomly presenting 38 stimuli in isolation, 10 of which were healthy voices and 28 with different degrees of deviation, so that each participant could classify them as normal or altered. In the second experiment, the participants heard only breathy and healthy voices with different degrees of deviation and had to discriminate the presence or absence of breathiness. The third experiment was similar to the second experiment but with a rough voice. Results: Women in the EG had a lower hit rate (52.2%) in identifying dysphonic voices than women in the CG (69.6%) (P < 0.001). The women in the EG had a lower accuracy rate in identifying predominantly rough (62.7%) and breathy (62%) voices, compared with the accuracy rate of the women in the CG (73% and 75.6%, respectively) (P value < 0.001). There was a moderate negative correlation between the hit rate of nondysphonic women and the shimmer values. Conclusions: Dysphonia can interfere with the identification of dysphonic voices. Dysphonic women had a lower accuracy rate in identifying dysphonia and roughness and breathiness parameters than nondysphonic women. © 2025 The Voice Foundation

关键词： Auditory perception—Dysphonia—Voice disorders—Vocal quality

来源：评论

学校读者我要写书评

暂无评论

New Combining Rules for Spatial Clustering Methods Using Sigma-Count for Spatial Epidemiology

New Combining Rules for Spatial Clustering Methods Using Sig...

引用

2020 International Conference on decision Aid Sciences and Application, DASA 2020

作者： De Sa, Laisa Ribeiro MacHado, Liliane Dos Santos De Almeida Nogueira, Jordana De Moraes, Ronei Marcos Graduate Program in Decision Models and Health Federal University of Paraiba João Pessoa Brazil Federal University of Paraiba Department of Informatics João Pessoa Brazil

ISBN: (纸本)9781728196770

In Epidemiology, the study of several diseases is related to the geographical territory in which it occurs. Some spatial clustering methods are able to perform statistical decision about the significance of territories. However, each method is based on a different methodology, providing different results as well. Recently, some authors proposed combining spatial clustering methods in order to provide more accurate results. This paper propose two new combining rules based on Cardinality of Fuzzy Sets, generalizing the classical Majority Voting and Plurality Voting. A study of case using real Dengue Fever epidemiological data and combining five spatial clustering methods was performed. In this study the Fuzzy Plurality Voting provided better decision map than the classical ones, when compared to a reference map. © 2020 IEEE.

关键词： Epidemiology

来源：评论

学校读者我要写书评

暂无评论

Volitional and Non-volitional Devices Used in Voice Therapy and Training: A Scoping Review—Part A

引用

Journal of Voice 2024年

作者： Batista, Denis de Jesus Duarte, João M. da Trindade Siqueira, Larissa T.D. Almeida, Anna A. Lopes, Leonardo W. Ribeiro, Vanessa V. Center for Exact and Natural Sciences Postgraduate program in Decision Models and Health of Universidade Federal da Paraíba Paraíba João Pessoa Brazil Health Sciences Center Associated Postgraduate Program in Speech-Language Pathology and Audiology at the Universidade Federal da Paraíba Universidade Federal do Rio Grande do Norte and Universidade Estadual de Ciências da Saúde de Alagoas Paraíba João Pessoa Brazil Center for Human Sciences Letters and Arts Postgraduate program in Linguistics of Universidade Federal da Paraíba Paraíba João Pessoa Brazil Department of Speech-Language Pathology and Audiology of the Universidade Federal do Rio Grande do Norte Rio Grande do Norte Natal Brazil Department of Speech-Language Pathology and Audiology Graduate Program in Linguistics and Graduate Program in Decision Models and Health of the Universidade Federal da Paraíba Paraíba João Pessoa Brazil Faculty of Medicine Speech-Language Pathology and Audiology course and the Postgraduate Program in Medical Sciences of the Universidade de Brasília Distrito Federal Brasília Brazil

Objective: To map the volitional and non-volitional devices used by speech and language pathologists (SLPs) in voice training and therapy and characterize their use in research on voice interventions. Methods: This scoping review is the first part of a larger study. The electronic search was carried out by mapping the references in PubMed/Medline, LILACS/BVS, Scopus, Web of Science, EMBASE, and the Cochrane Library, and the manual search was carried out in the grey literature. Two blind independent reviewers selected and extracted data;divergences were solved by consensus. The data extracted in this part of the study were the authorship and year of publication, country, study design, sample characteristics, intervention modality, ingredient, target, mechanism of action, dosage, and outcome measures. They were addressed with descriptive analysis. Results: Publications that use devices as ingredients are mostly from the last two decades, mainly carried out in the United States of America and Brazil, in adults of both sexes with behavioral dysphonia. Forty-two types of devices were used, many of them with similar approaches but different nomenclatures. Most devices were used voluntarily, focusing on vocal function, and aiming to increase source and filter interaction. Most studies used silicone tubes. The most reported technical specification to apply the ingredient was surface electrodes on the neck. Device dosage was time-controlled, and the most used outcomes were self-assessment and acoustic analysis. Conclusion: Devices are currently used as ingredients in vocal interventions, with a greater focus on increasing the source and filter interaction, associated with silicone tubes (the most used devices in these studies), which have been dosed with performance time. Outcomes were measured with self-assessment instruments. © 2023 The Voice Foundation

关键词： Language and hearing sciences Speech Speech therapy Voice Voice disorders Voice training

来源：评论

学校读者我要写书评

暂无评论

New Combining Rules for Spatial Clustering Methods Using Sigma-Count for Spatial Epidemiology

New Combining Rules for Spatial Clustering Methods Using Sig...

引用

decision Aid Sciences and Application (DASA), International Conference on

作者： Laisa Ribeiro de Sá Liliane dos Santos Machado Jordana de Almeida Nogueira Ronei Marcos de Moraes Graduate Program in Decision Models and Health Federal University of Paraiba João Pessoa Brazil Federal University of Paraiba João Pessoa Brazil

ISBN: (数字)9781728196770

ISBN: (纸本)9781728196787

关键词： Clustering methods Statistics Sociology Fuzzy sets Epidemiology Indexes Diseases

来源：评论

学校读者我要写书评

暂无评论

Incisions in virtual reality simulators: assessing user performance

引用

Research on Biomedical Engineering 2019年第2期35卷 103-110页

作者： de Moura, Ives Fernando Martins Santos Machado, Liliane dos Santos Valença, Ana Maria Gondim Graduate Program in Decision Models and Health LabTEVE/Department of Statistics Federal University of Paraíba Cidade Universitária s/n – Castelo Branco João Pessoa58051-900 Brazil Department of Informatics Federal University of Paraíba Cidade Universitária s/n – Castelo Branco João Pessoa58051-900 Brazil

Purpose: The use of simulators based on virtual reality has become more common in different areas. In the field of health sciences, their use ranges from the training of future professionals to planning and performing surgical procedures in real cases. Different procedures can be trained through these programs, one of them being the surgical incision. It was identified that although there are different applications capable of simulating incisions, there was no specific method to assess the performance of the user who was involved in this task, something that would be fundamental for the learning process. Methods: The structure and the variables used in the proposed assessment system for surgical incisions performed in simulators were obtained from the literature of the area and the decision models support vector machine and classical logic were chosen after performing tests with a data set of simulated incision examples. Results: The assessment system is presented as the main result and a simulation of a specific type of incision (submental) was developed to validate it. Satisfactory results were obtained in the tests, with 74 to 97% of accuracy, depending on the test configuration. Conclusion: The tests indicate that the system in its current format is a good candidate for testing and eventual use with human users in a training environment. © 2019, Sociedade Brasileira de Engenharia Biomedica.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：