Background: Pathological speech diagnosis is crucial for identifying and treating various speech disorders. Accurate diagnosis aids in developing targeted intervention strategies, improving patients' communication abilities, and enhancing their overall quality of life. With the rising incidence of speech-related conditions globally, including oral health, the need for efficient and reliable diagnostic tools has become paramount, emphasizing the significance of advanced research in this field.
Methods: This paper introduces novel features for deep learning in the analysis of short voice signals. It proposes the incorporation of time-space and time-frequency features to accurately discern between two distinct groups: Individuals exhibiting normal vocal patterns and those manifesting pathological voice conditions. These advancements aim to enhance the precision and reliability of diagnostic procedures, paving the way for more targeted treatment approaches.
Results: Utilizing a publicly available voice database, this study carried out training and validation using long short-term memory (LSTM) networks learning on the combined features, along with a data balancing strategy. The proposed approach yielded promising performance metrics: 90% accuracy, 93% sensitivity, 87% specificity, 88% precision, an F score of 0.90, and an area under the receiver operating characteristic curve of 0.96. The results surpassed those obtained by the networks trained using wavelet-time scattering coefficients, as well as several algorithms trained with alternative feature types.
Conclusions: The incorporation of time-frequency and time-space features extracted from short segments of voice signals for LSTM learning demonstrates significant promise as an AI tool for the diagnosis of speech pathology. The proposed approach has the potential to enhance the accuracy and allow for real-time pathological speech assessment, thereby facilitating more targeted and effective therapeutic interventions.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.compbiomed.2024.107976 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Interprofessional education stroke workshop: case-based learning for occupational therapy and speech-language pathology students.
J Interprof Care
January 2025
Speech-Language Pathology and Audiology, Towson University, Towson, MD, USA.
Collaboration between occupational therapists and speech-language pathologists is crucial in stroke rehabilitation to effectively manage the complex challenges patients often experience after stroke. This article describes a two-hour, case-based interprofessional education (IPE) stroke workshop that required 67 graduate occupation therapy (OT) and speech-language pathology (SLP) students to collaboratively solve a case study related to stroke. Students used a survey to self-assess their interprofessional collaborative practice before and after participating in the workshop and completed a reflection journal.
View Article and Find Full Text PDFA Pilot Trial of Tongue Reconstruction Using the Chimeric Innervated Vastus Lateralis Muscle and Antero-Lateral Thigh Free Flap.
Head Neck
January 2025
Department of Head and Neck Surgery, Chris O'Brien Lifehouse, Sydney, Australia.
Background: Subtotal and total glossectomies for advanced tongue cancer result in significant speech- and swallow-related morbidity, impairing quality of life. This prospective pilot study compares the safety and functional outcomes associated with using a chimeric innervated muscle and fasciocutaneous flap for soft tissue reconstruction.
Materials And Methods: A prospective, non-randomized controlled pilot study evaluated a standardized technique for tongue reconstruction using a chimeric innervated vastus lateralis muscle and anterolateral thigh fasciocutaneous flap.
Speech-Language Pathology Preservice Preparation for Working in School-Age Literacy: International Perspectives.
Lang Speech Hear Serv Sch
January 2025
School of Education, La Trobe University, Bendigo, Victoria, Australia.
Purpose: This narrative review of preservice training of speech-language pathologists (SLPs) to work in school-age literacy contexts examines (a) studies regarding SLPs' perceptions of their preservice training and (b) accreditation requirements for preservice training in selected nations.
Method: A review of the literature examining (a) SLPs' perspectives about their preservice training; (b) SLPs' beliefs, confidence, and self-efficacy; and (c) speech-language pathology preservice program content was conducted via analysis of studies published after the year 2010. Policy documents and websites outlining accreditation requirements in the United States, Canada, the United Kingdom, Australia, and New Zealand were reviewed.
Performance analysis of a deep-learning algorithm to detect the presence of inflammation in MRI of sacroiliac joints in patients with axial spondyloarthritis.
Ann Rheum Dis
January 2025
Rheumatology Department, Cochin Hospital, Paris, France; INSERM (U1153): Clinical Epidemiology and Biostatistics, University of Paris, Paris, France.
Objectives: To assess the ability of a previously trained deep-learning algorithm to identify the presence of inflammation on MRI of sacroiliac joints (SIJ) in a large external validation set of patients with axial spondyloarthritis (axSpA).
Methods: Baseline SIJ MRI scans were collected from two prospective randomised controlled trials in patients with non-radiographic (nr-) and radiographic (r-) axSpA (RAPID-axSpA: NCT01087762 and C-OPTIMISE: NCT02505542) and were centrally evaluated by two expert readers (and adjudicator in case of disagreement) for the presence of inflammation by the 2009 Assessment of SpondyloArthritis International Society (ASAS) definition. Scans were processed by the deep-learning algorithm, blinded to clinical information and central expert readings.
Assessing the Clinical and Functional Status of COPD Patients Using Speech Analysis During and After Exacerbation.
Int J Chron Obstruct Pulmon Dis
January 2025
Department of Cardiology, Respiratory Medicine and Intensive Care, University Hospital Augsburg, Augsburg, Germany.
Background: Chronic obstructive pulmonary disease (COPD) affects breathing, speech production, and coughing. We evaluated a machine learning analysis of speech for classifying the disease severity of COPD.
Methods: In this single centre study, non-consecutive COPD patients were prospectively recruited for comparing their speech characteristics during and after an acute COPD exacerbation.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!