Description
This Open Access book provides a comprehensive exploration of voice as a biomarker, addressing a current issue where engineers often analyze voice using sentences without describing or understanding voice as a set of defined parameters among others visually. This approach poses challenges for effectively treating voice disorders, as the features defined by engineers may not align with clinical needs.
Stemming from the work of the Biomarker Committee group under the European Union of Phoniatricians (UEP), this book is the result of collaborative efforts and presents clinical studies aimed at bridging the gap between engineering analyses and clinical requirements.
In recent years, many engineers have utilized software for voice analysis, often within continuous speech sequences, but without adequately defining voice features or specifying the choice of machine learning programs.
Organized into 14 chapters, the volume begins with an overview of voice biomarkers and relevant literature, covering the fundamental physiology of voice biomarkers and examining voice pathology. The last chapters discuss genetics and molecular biology aspects.
This book will serve as an invaluable resource for medical specialists in otolaryngology, phoniatrics, and neurology, offering insights and approaches to enhance the understanding and treatment of voice-related conditions.
Preface.- . Methods.- 1. Committee on Biomarkers in Phoniatrics, Introduction.- 2. Overview of Voice Parameters in Parkinson s Disease Allegedly as Biomarkers.- 3. AI-enhanced Voice Analysis for Neurologic Diseases.- 4. Modelling a Pre-clinical Screening Tool Based on Voice Biomarkers: The Case of Parkinson s Disease.- 5. Glottal Inverse Filtering and Its Application in Automatic Classification of Diseases.- 6. (Bio)-markers and AI in Voice Disorders (Parkinson s Disease): Opportunities and Challenges.- 7. Voice-related Biomarkers 2nd Union of European Phoniatricians/European Academy of Phoniatricians-British Laryngology Association, Joint Meeting.- 8. Software and Apps for Inverse Filtering of The Voice.- 9. Voice-related Biomarkers and Speech Measurements Determined with AI.- . Clinical Applications.- 10. Pathology of Voice-related Biomarkers in Laryngology.- 11. Voice-related Biomarkers in Neurodegenerative Disorders.- 12. Aspects of Genetics and Voice-related Biomarkers.- 13. Optical Coherence Tomography and Voice-related Biomarkers.- 14. Conclusion.
Mette Pedersen has had an Ear, Nose, and Throat clinic at The Medical Center Østergade 18 in Copenhagen and is now a consultant there. She serves as a Danish Representative in the Union of European Phoniatricians (UEP). Additionally, she is a member of the Committee of Voice Biomarkers and is a senior researcher working on many projects, including optical coherence tomography, among others, in collaboration with the Department of Electrical and Photonics Engineering at the Danish Technical University, Lyngby, Denmark.
Valentina Camesasca is an Ear, Nose, and Throat and Head & Neck Surgeon specialist and a higher educated Phoniatrician with extensive training in voice and swallowing. She is a member of the UEP Committee of Voice Biomarkers and works at Great Metropolitan Niguarda Hospital and NEMO (NeuroMuscolar) Clinical Center in Milan. She has participated in and presented papers at many national and international conferences, with her research including topics such as endoscopies.
Neveen Hassan Nashaat works as a professor of phoniatrics, communication and audiology. She is an educated Ear, Nose, and Throat specialist and phoniatrician with extensive training in voice and swallowing from faculty of medicine Ain Shams University in Cairo. She is a member of the UEP Committee of Voice Biomarkers.
Ramón Hernández-Villoria is a Medical Doctor, Phoniatrician specialist, Public Health specialist and M.Sc. in Linguistics. He is a Committee of Voice Biomarkers member and works at Centro Clínico de Audición y Lenguaje in Caracas, Venezuela. He is the Union of European Phoniatricians' national representative in his country. He has been a full professor and visiting professor at various universities in undergraduate and graduate studies in phoniatrics, speech therapy, and occupational medicine for twenty-five years. He has published research in applied phonetics and occupational voice and presented at international conferences.
Sneha Das (DSc.) is an assistant professor at the Technical University of Denmark, specializing in speech and voice technology. Her work focuses on the intersection of voice analysis, machine learning, and biomedical applications. She holds a PhD in speech and language technology and has contributed to several international projects on health-related speech processing and AI. Sneha s research emphasizes on the safe application of AI in healthcare and critical infrastructure, and low-resource machine learning for healthcare.
