检索结果-内蒙古大学图书馆

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

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

Mobile Applications Used for Vocal Health: An Integrative Review

引用

Journal of Voice 2025年

作者： Penha, Patrícia Brianne da Costa Mendes, Amanda Louize Félix Guedes, Aline de Menezes Santos, Cláudio da Cruz Duarte, Lorena Sampaio Lima-Silva, Maria Fabiana Bonfim de Associated Postgraduate Program in Linguistics – PROLING Federal University of Paraíba (UFPB) Paraíba João Pessoa Brazil Associated Postgraduate Program in Speech-Language-Hearing Sciences Federal University of Paraíba (UFPB) Paraíba João Pessoa Brazil Speech-Language-Hearing Pathologist Federal University of Paraíba (UFPB) Paraíba João Pessoa Brazil Department of Speech Therapy Federal University of Paraíba (UFPB) Paraíba João Pessoa Brazil

This article aimed to verify the possible advantages of using mobile applications to promote vocal health and monitor vocal rehabilitation. This integrative review researched five scientific databases, using the descriptors “voice” and “smartphone” or “mobile applications” or “software” and “speech-language.” The search yielded 570 articles, of which seven were included after careful analysis. The studies reveal that application use can assist in the rehabilitation process and raise patient/user awareness about the importance of voice care. Mobile applications aimed at vocal promotion or monitoring generate advantages for speech-language-hearing pathologists and patients/users, such as easy access and use, strengthening the bond between professionals and patients, and encouraging patients/users to change their vocal behaviors positively. © 2025

关键词： Voice—Smartphone—Mobile applications—speech therapy—speech, language, and hearing science

来源：评论

学校读者我要写书评

暂无评论

Assessing sensitivity to semantic and syntactic information in deaf readers: An ERP study

引用

Neuropsychologia 2025年 215卷 109171页

作者： Emmorey, Karen Akers, Emily M. Martinez, Priscilla M. Midgley, Katherine J. Holcomb, Phillip J. School of Speech Language and Hearing Sciences SDSU United States Joint Doctoral Program in Language and Communication Disorders SDSU and UCSD United States Department of Psychology SDSU United States

An ERP study by Mehravari et al. (2017) found deaf and hearing readers had similar N400 effects to semantic violations, but only hearing readers showed a P600 effect to verb agreement violations. To assess whether lack of sensitivity to agreement was due to early language deprivation, we presented the same stimuli (and a phrase structure violation condition) to deaf readers with early ASL exposure and a reading-matched hearing group. We also examined N400 “wrap up” effects for sentence final words. Both groups exhibited an N400 effect for semantic violations (larger negativities for errors), although the effect was unexpectedly weak for hearing readers. At the violation, only hearing readers exhibited a P600 for verb agreement violations (larger positivities for errors), indicating that the previous findings are not explained by language deprivation. Crucially, both groups exhibited an N400 effect on the sentence-final word for agreement violations – despite poor performance on the acceptability judgment task. Both deaf and hearing readers showed a robust P600 to phrase structure violations. We interpret this overall pattern as indicating that deaf readers engage in monitoring strategies whereby English phrase structure, but not verb morphology, is anticipated during reading, and that both groups exhibit neural sensitivity to grammatical errors during sentence final integration processes. The amplitude of the P600 for grammatical violations was correlated with reading skill only for hearing readers. We conclude that reading strategies for skilled deaf readers who are bilingual in ASL differ from hearing monolingual readers with similar reading skills. © 2025 The Authors

关键词： Deaf readers ERPs N400 P600 Phrase structure violations Semantic violations Verb agreement

来源：评论

学校读者我要写书评

暂无评论

Effectiveness of Telerehabilitation Exercise programme on Disability and Pain in Patients With Chronic Non-Specific Neck Pain: Randomised Controlled Trial Assessor-Blinded

引用

Musculoskeletal Care 2025年第2期23卷 e70119页

作者： Barbosa, Juliene Corrêa da Luz, Bruna Vale da Silva, Breno Felipe Portal Marques, Amelia Pasqual Saragiotto, Bruno Tirotti Comachio, Josielli Magalhaes, Mauricio Oliveira Master's Program in Human Movement Sciences Federal University of Pará Belém-Pará Brazil Faculty of Physiotherapy and Occupational Therapy Federal University of Pará Belém-Pará Brazil Department of Physiotherapy Rehabilitation Sciences Program Speech-Language Pathology and Audiology and Occupational Therapy Faculty of Medicine University of São Paulo São Paulo Brazil Master's Programs in Physical Therapy Universidade Cidade de São Paulo São Paulo Brazil Sydney Musculoskeletal Health School of Health Sciences Charles Perkins Centre Faculty of Medicine and Health University of Sydney Sydney Australia

Introduction: Chronic neck pain is an important public health problem. Telerehabilitation has emerged as an important tool for individuals with musculoskeletal conditions. Objectives: The study aims to identify the effectiveness of a telerehabilitation exercise programme compared with a digital self-care booklet on non-specific neck pain. Methods: A randomised controlled trial assessor-blinded, 3 months follow-up. 70 patients were randomised into two groups of 35. The telerehabilitation group received 6 weeks of individualised training through vídeo calls and an online booklet. The control group received an online booklet. The primary outcome was functional disability. Secondary outcomes included pain intensity, global perceived effect, self-efficacy, quality of life, and kinesiophobia. All outcomes were assessed at baseline, 6 weeks, and a 3-month follow-up. Results: There was a significant difference between groups for functional disability (Mean 10.3, CI 95% 4.8–15.7), pain intensity (Mean 2.8, CI 95% 1.4–4.1), global perceived effect (Mean −2.3, CI 95% −3.7 to −0.9), and self-efficacy (Mean −24.7, CI 95% −41.0 to −8.4) at the 6-week. At the 3-month follow-up, statistically significant differences were observed for perceived overall effect (Mean −2.0, CI 95% −3.4 to −0.6) and self-efficacy (Mean −26.3, CI 95% −42.8 to −9.8). Conclusions: Telerehabilitation is effective in improving disability and pain intensity compared with self-care booklets only in individuals with non-specific chronic neck pain. Trial registration: This trial is registered at https://***/rg/RBR-10h7khvk under the registration number RBR10h7khvk at 09/16/2022. © 2025 The Author(s). Musculoskeletal Care published by John Wiley & Sons Ltd.

关键词： chronic pain exercise therapy neck pain telehealth telerehabilitation

来源：评论

学校读者我要写书评

暂无评论

speech auditory brainstem responses and words-in-noise recognition scores: Is there a link?

Speech auditory brainstem responses and words-in-noise recog...

引用

作者： Lagacé, Josée Koravand, Amineh Thompson, Jordon Lteif, Suzanne Audiology and Speech-Language Pathology Program Health Sciences Faculty University of Ottawa Ottawa Canada

A study was conducted to investigate possible relationship between variables of cABR and the performance measured at a word-in-noise recognition task on adults. This is part of a larger study aiming at developing a screening tool for listening difficulties in noise for young children. Forty-three normal hearing adults from 18 to 30 years old participated in this study. They had no history of hearing problems or language development difficulties. The average score was lower when words were presented with an ipsilateral white noise (noise condition). As expected, the Group 3 who was exposed to a higher noise level had the lowest average correct score. Only one correlation between speech recognition score in noise with one cABR variable at only one SNR condition, which is not sufficient at this point to suggest any link between cABR and hearing in noise.

关键词： Audition

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Listening Rate Preferences for Oral Reading and Impromptu Speaking Tasks

引用

Journal of Communication 1973年第1期23卷 95-102页

作者： Lass, Norman J. Prater, C. Elaine Norman J. Lass (Ph.D. Purdue University 1968) is Assistant Professor of Speech and Hearing Sciences and Director of the Speech and Hearing Sciences Laboratory at West Virginia University C. Elaine Prater (B.S. West Virginia University 1971) was formerly a student in the Speech Pathology-Audiology program and a research assistant in the Speech and Hearing Sciences Laboratory at West Virginia University. She is presently a graduate student in the Audiology and Speech Pathology program at Memphis State University

A paired comparison paradigm was employed to compare the listening rate preferences of 26 adult subjects for oral reading and impromptu speaking tasks. Recordings of a reading and speech were time‐altered by means of a speech compressor to yield nine rates: 100, 125, 150, 175, 200, 225, 250, 275, and 300 wpm. Two master tapes were constructed, one for each of the two tasks investigated. The tapes were presented to each subject for listening rate preference judgments. Results of subjects'evaluations indicate that preferred listening rates are very similar for both oral reading and impromptu speaking tasks. The most preferred rate for both tasks was 175 wpm, and the least preferred rate for both tasks was 100 wpm. Comparison of the present findings with previous research and suggestions for future investigations are provided. Copyright © 1973, Wiley Blackwell. All rights reserved

关键词：

来源：评论

学校读者我要写书评

暂无评论

Effectiveness of an online continuing education course in infant hearing health for primary care professionals

引用

International audiology 2023年第5期62卷 453-461页

作者： Maria Taiany Duarte de Oliveira Kátia de Freitas Alvarenga Krisia Thayná Lima da Costa Vanessa Boldarini Godoy Regini Sheila Andreoli Balen Lilian Cassia Bornia Jacob-Corteletti Eliene Silva Araújo a Graduate Program in Speech Language and Hearing Sciences Federal University of Rio Grande do Norte Natal Brazil b Audiology Research Center Research Group Department of Speech-Language Pathology and Audiology Speech-Language Pathology and Audiology Graduate Program Bauru School of Dentistry/University of São Paulo FOB/USP Bauru Brazil c Graduate Program in Speech Language and Hearing Sciences Bauru School of Dentistry University of São Paulo FOB/USP Bauru Brazil d Laboratory of Technological Innovation in Health Department of Speech-Language Pathology and Audiology Graduate Program in Speech Language and Hearing Sciences Onofre Lopes University Hospital Federal University of Rio Grande do Norte Natal Brazil e Department of Speech-Language Pathology and Audiology Graduate Program in Speech Language and Hearing Sciences Federal University of Rio Grande do Norte Natal Brazil

ObjectiveTo evaluate the effectiveness of an online continuing education course on infant hearing health for primary care *** prospective longitudinal study with interrupted time series pre-test/post-test design. The effectiveness of the online course was assessed by comparing ***-training performance and analysing responses to evaluations of the quality of the *** sampleThe sample comprised individuals enrolled between September 2018 and August 2019 in a Ministry of Health course, “Actions in primary care for the early identification of hearing impairment” offered on the AVASUS *** the 2908 individuals registered, 1842 (63.3%) completed the course. Their ages ranged from 18 to 77 years, and 67.4% of them were females. Students and doctors were overrepresented among the enrollees. All Brazilian states were included in the sample. Comparisons of pre- and post-training performances showed a significant improvement in knowledge, and 99.3% of the participants provided positive comments regarding the quality of the *** course is an effective distance learning tool on infant hearing health for primary care professionals. The online course circumvents the limitations posed by geographical barriers and also facilitates decentralisation.

关键词： Capacity building in service community health worker neonatal screening hearing virtual learning environment

来源：评论

学校读者我要写书评

暂无评论

A Canadian version of the digit triplets test 26

A Canadian version of the digit triplets test

引用

26th International Congress on Sound and Vibration, ICSV 2019

作者： Lagacé, Josée Giguère, Christian Kathleen Pichora-Fuller, M. Audiology and Speech-Language Pathology Program Faculty of Health Sciences University of Ottawa OttawaON Canada Department of Psychology University of Toronto MississaugaON Canada

ISBN: (纸本)9781999181000

Of all the stimuli used for speech-in-noise tests, digits have received a particular attention as stimuli because they are highly familiar words to all age groups, including populations learning a new language. The Digit Triplets Test (DTT;Smits et al., 2004) was originally developed in the Dutch language as an automatic self-screening test. The test uses an adaptive procedure to find the speech recognition threshold (SRT) in noise, which corresponds to the signal-to-noise ratio at which the digit triplets are correctly identified 50% of the time. The DTT has been adapted in different languages and can be administered over the phone, the internet, or smartphones. Digits triplets (e.g., 4-1-8) are presented in a background noise and the listener enters the digits heard on a keypad. A Canadian French and English version of the DTT has been developed in a collaborative effort between the University of Ottawa and the University of Toronto (CDTT). The digits were recorded in both languages from two fluently bilingual adult talkers (one male, one female). The recordings were then processed and optimized, according to the ICRA recommendations (2015) and ISO standard on speech audiometry (ISO 8253-3:2012). A speech-shaped noise was developed for each language-talker combination. This presentation will describe the development stages of the CDTT. Data obtained with normal hearing adults and school-aged children using the CDTT software will be presented, as well as some metrics and characteristics of the test (e.g., test-retest reliability, etc.). Some details about the required hardware will also be presented for laptop implementation. The CDTT requires little practice and can be quickly administered, making it ideal for measuring speech-in-noise performance with many populations, including in children or non-native speakers of French or English © Proceedings of the 26th International Congress on Sound and Vibration, ICSV 2019. All rights reserved.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Modeling perceived vocal age in American English

Modeling perceived vocal age in American English

引用

作者： Harnsberger, James D. Shrivastav, Rahul Brown Jr., W.S. Program in Linguistics University of Florida United States Department of Speech Language and Hearing Sciences University of Florida United States

An acoustic analysis of voice, articulatory, and prosodic cues to perceived age was completed for a speech database of 150 American English speakers. Perceived ages were submitted to multiple linear regression analyses with measures of acoustic correlates of: voice quality, articulation, fundamental frequency, and prosody. The fit between predicted and actual perceived ages from the resulting models varied by speech material and gender, with female vocal ages being the easiest to predict. Articulation, pitch, and speaking rate measures were the most predictive in female voices, while, for male voices, the observed ranking was: speaking rate, voice quality, and pitch. © 2010 ISCA.

关键词： speech communication

来源：评论

学校读者我要写书评

暂无评论

Perceptual integration of visual evidence of the airstream from aspirated stops

引用

Canadian Acoustics - Acoustique Canadienne 2013年第3期41卷 23-27页

作者： Mayer, Connor Gick, Bryan Weigel, Tamra Whalen, D.H. Department of Computer Science University of British Columbia Vancouver BC Canada Department of Linguistics University of British Columbia Vancouver BC Canada Haskins Laboratories New Haven CO United States School of Audiology and Speech Sciences University of British Columbia Vancouver BC Canada Program in Speech-Language-Hearing Sciences City University of New York New York United States

This study investigates whether indirect visual evidence of aspiration can influence speech perception as previously found for tactile information. Participants were shown video of a speaker producing the sequence pom and "bomb" in a noisy setting. In some tokens, a candle was visibly perturbed by aspiration. All participants were more likely to correctly identify "ppm" and incorrectly identify "bomb" in the presence of visible perturbation, indicating that perceptual integration was taking place. This effect was stronger for participants who reported being consciously aware of the candle as a predictor. This indicates that ambient information can be incorporated in speech perception even when presented via an indirect modality, and that active attention can amplify this effect.

关键词： Bombs (ordnance)

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：