Category Ranking
98%
Total Visits
921
Avg Visit Duration
2 minutes
Citations
20
Article Abstract
Background And Objective: Speech disorders can arise from various causes, including congenital conditions, neurological damage, diseases, and other disorders. Traditionally, medical professionals have used changes in voice to diagnose the underlying causes of these disorders. With the advancement of artificial intelligence (AI), new possibilities have emerged in this field. However, most existing studies primarily focus on comparing voice data between normal individuals and those with speech disorders. Research that classifies the causes of these disorders within the abnormal voice data, attributing them to specific etiologies, remains limited. Therefore, our objective was to classify the specific causes of speech disorders from voice data resulting from various conditions, such as stroke and hearing impairments (HI).
Methods: We experimentally developed a deep learning model to analyze Korean speech disorder voice data caused by stroke and HI. Our goal was to classify the disorders caused by these specific conditions. To achieve effective classification, we employed the ResNet-18, Inception V3, and SEResNeXt-18 models for feature extraction and training processes.
Results: The models demonstrated promising results, with area under the curve (AUC) values of 0.839 for ResNet-18, 0.913 for Inception V3, and 0.906 for SEResNeXt-18, respectively.
Conclusions: These outcomes suggest the feasibility of using AI to efficiently classify the origins of speech disorders through the analysis of voice data.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC12118888 | PMC |
| http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0315286 | PLOS |
Publication Analysis
Top Keywords
Similar Publications
Exploring Early Perceptions and Experiences of ChatGPT in Pediatric Critical Care: A Qualitative Study Among Health Care Professionals.
Clin Pediatr (Phila)
September 2025
College of Medicine, King Saud University, Riyadh, Saudi Arabia.
To optimize the deployment of Generative Artificial Intelligence in health care, it's essential for health care professionals (HCPs) to understand these technologies' capabilities and constraints. This study explores HCPs' initial impressions and experiences using ChatGPT, a Generative Pre-trained Transformer, in Pediatric Critical Care Units (PICUs). By conducting focus groups with a diverse set of HCPs, we aimed to assess their awareness, utilization, perceived benefits, and concerns about incorporating ChatGPT into their PICUs.
View Article and Find Full Text PDFChallenges and Limits in Explaining and Acoustic Modeling of Voice Characteristics.
J Voice
September 2025
Bielefeld University, P.O. Box 10 01 31, Bielefeld D-33501, Germany. Electronic address:
To this day, the assessment of human voices remains a challenge due to (i) inconsistencies in subjective ratings and (ii) the lack of objective measurements for the perceptual impressions of voice characteristics. This can lead to significant consequences in applied fields such as speech therapy, where the assessment of voices is crucial for a successful treatment. In this paper, we address the explanation of voice and its characteristics from two different angles: In a first study, 22 speech therapists in training assessed a set of 20 non-pathological voices regarding 20 voice characteristics before and after receiving an expert explanation.
View Article and Find Full Text PDFFinding the Voices: Representation of Nurses in Dutch Newspaper Media Between 2019 and 2022.
Int Nurs Rev
September 2025
Department of Health Studies, The Research Group for Person-Centeredness in an Ageing Society, Fontys University of Applied Sciences, Eindhoven, The Netherlands.
Aim: To explore how nurses were represented in five Dutch newspapers between 2019 and 2022, with a focus on their visibility in policy and decision-making.
Background: The media significantly shape public understanding of healthcare. Despite their key role, nurses are often underrepresented in media, especially in policy-related coverage.
Lessons from the scale-up of provider-administered and self-injection of DMPA-SC in Nigeria: a landscape assessment.
BMC Womens Health
September 2025
Department of Community Medicine, University of Jos, P. M. B. 2084, Jos, Plateau State, Nigeria.
Background: Nigeria is the seventh-most populous country in the world. Its high fertility rate and unmet need for family planning contribute to the increasing population size. To reduce this gap, the Federal Government of Nigeria, in collaboration with Injectables Access Collaborative and other public and private sector players, introduced the subcutaneous depot medroxyprogesterone acetate (DMPA-SC) to the contraceptive method mix in 2017.
View Article and Find Full Text PDFThe Experiences of Transgender and Gender Diverse Individuals After Intonation Training for a More Masculine-Sounding Voice: A Qualitative Study.
J Voice
September 2025
Center for Speech and Language Sciences (CESLAS), Department of Rehabilitation Sciences, Ghent University, Ghent, Belgium; Department of Otorhinolaryngology and Head and Neck Surgery, Ghent University Hospital, Ghent, Belgium.
Introduction: A significant challenge for some transgender and gender diverse (TGD) individuals is that their voice and communication do not align with their gender identity or the way they wish to be perceived. Voice and communication training (VCT) can address key factors that are the most salient in gender perception, such as pitch, resonance, articulation, and intonation. While intonation training has proven its benefits for developing a feminine-sounding voice, its impact on achieving a masculine-sounding voice remains underexplored.
View Article and Find Full Text PDF