Knowledge

WEVOSYS medical technology GmbH

Here you will find current and past research projects in which WEVOSYS is or was involved, book recommendations on the subject of voice & speech and scientific publications in which lingWAVES was used.

Research and development

WEVOSYS has been an internationally recognised and leading provider of modern and innovative systems for clinical voice and speech processing, documentation and diagnostics for over 20 years. documentation and diagnostics. The success of the systems is based not only on high quality, modernity and customer proximity, but also on continuous further development based on on the basis of the latest scientific findings, gained both in co-operation with clinics and universities and in our own research laboratory. Projects are also realised projects are also subsidised by the Federal Ministry for Economic Affairs and Energy, for example, due to the high level of innovation.

Supported by

Multi-modal based quantitative voice and larynx diagnostics using machine learning

Cooperation partner: University Hospital Erlangen, Ear, Nose and Throat Clinic, Head and Neck Surgery, Department of Phoniatrics and Pediatric Audiology

Period: January 2025 - December 2027

High-speed endoscopic imaging (HSE) will replace stroboscopy for laryngeal diagnostics in ENT/phoniatrics in the medium term. Thanks to the applicants' predecessor project, the HSE method now allows rapid processing of video data and initial quantitative assessments of laryngeal and vocal fold dynamics. The next logical step is valid quantitative diagnostics for documentation as therapy progress monitoring (i.e. graduation of the disorder before, during and after conservative therapy, surgery or radiotherapy). This does not yet exist. This project aims to close this gap: The aim of the project is to apply current methods of machine learning (artificial intelligence - AI) to enable multi-parametric based on current imaging methods (HSE) and the synchronously recorded acoustic signal a quantitative diagnosis and therapy progression control with regard to laryngeal functionality and voice quality.

Funding program: “Central Innovation Program for SMEs” of the Federal Ministry of Economics and Climate Protection (BMWK)

Medinym - AI-based anonymisation of personal patient data in clinical text and voice databases

The project ‘AI-based anonymisation of personal patient data in clinical text and voice databases’ (Medinym) investigates the possibility of further processing sensitive data by removing sensitive information through anonymisation. Two medical use cases, text-based data from electronic patient records and voice data from diagnostic doctor-patient consultations, are being implemented as examples in the project. To this end, open technologies for anonymisation are being investigated, further developed and applied to real data. The researchers are also investigating how the informative value of such anonymised data can be preserved for further use. Methods that prevent or hinder misuse of the technology outside of the intended use case will also be considered.

Development of a system for high-speed endoscopy (HSE) for clinical laryngeal examinations

In the planned High Speed Endoscopy (HSE) project, a clinically applicable system is to be developed in co-operation with two partners, which will enable an improved laryngeal examination of the larynx in the clinical ENT field on the basis of new and state-of-the-art technologies. The HSE system is intended to offer doctors a new and modern alternative to conventional endo-stroboscopy systems, which uses extremely high frame rates (up to 8,000 fps) to visualise the vibration of the vocal folds in a natural way and can therefore provide new and enhanced information on the laryngeal voice function of the larynx. The aim and background here is to improve the diagnosis and treatment of patients. Due to the scientific-application-specific complexity and the goal of a clinically practicable application procedure, the project requires a close partnership of clinical research.

Assistance system for the automated detection and documentation of voice and speech disorders in clinical settings (AEDS)

The normal function of the voice is an essential prerequisite for spoken language communication. Its dysfunction causes limitations in verbal and non-verbal as well as private and professional communication The voice disorder (dysphonia) often only manifests itself in speech utterances. In the affected patient groups, voice diagnostics based on recorded phonations are not representative or are impossible due to limited co-operation and are therefore not suitable for diagnosing dysphonia. Necessary objectivisations in the context of assessments of communication skills or for the indication and testing of the effectiveness of medical treatment and therapy procedures are not possible here with the diagnostic procedures available in routine clinical practice. - The aim of this project is to develop an automated and standardised measurement procedure that describes the extent of the disorder in a qualitatively and quantitatively objectified way using CONTINUOUS speech, in contrast to the previous assessment based on sustained vowels or subjective hearing tests.

Nasality/nasalance - a new procedure

In the first quarter of 2015, a new method for acoustic measurement of nasalance (nasalisation) was developed. The nasalance measurement acoustically determines the velopharyngeal closure of a patient during speech by separately recording oral and nasal signals and then calculating the percentage ratio of oral to nasal.

Cooperation partner

Department of Phoniatrics and Paediatric Audiology

Prof. Dr. med. A. Schützenberger Prof. Dr.-Ing. M. Döllinger

Friedrich-Alexander University Erlangen-Nürnberg

Prof. Dr.-Ing. M. Döllinger

Specialist area Mobile Dialogue Systems

Jun.-Prof. Ingo Siegert

Averbis

Philipp Daumke

Artificial lntelligence Lab

Prof. Sebastian Stober

Medical clinic

Prof. Klemens Budde

Speech and Language Technology

Dr. Tim Polzehl

Quality and Usability Lab

Prof. Sebastian Möller

Department of Phoniatrics and Paediatric Audiology

Prof. Dr. med. A. Schützenberger Prof. Dr.-Ing. M. Döllinger

Friedrich-Alexander University Erlangen-Nürnberg

Prof. Dr.-Ing. M. Döllinger

Specialist area Mobile Dialogue Systems

Jun.-Prof. Ingo Siegert

Averbis

Philipp Daumke

Artificial lntelligence Lab

Prof. Sebastian Stober

Medical clinic

Prof. Klemens Budde

Speech and Language Technology

Dr. Tim Polzehl

Quality and Usability Lab

Prof. Sebastian Möller

The Department of Phoniatrics and Paediatric Audiology has been headed by Prof. Dr A. Schützenberger and Prof. Dr M. Döllinger since 12/2017. The main field of research is clinical laryngeal high-speed endoscopy (HSE), which the department has been working on since the mid-1990s. Since then, the department, together with other groups, has been a world leader in the scientific and clinical application of HSE. The department has developed its own research software for HSE image segmentation and quantitative analysis of vocal fold vibrations recorded with HSE. In a project funded by the BMWi (2018 – 2021), the department was able to develop clinically applicable HSE analysis software with the company WEVOSYS for the first time. The basic prerequisite for this was also the fully automated image segmentation based on neural networks, which was developed in the department. The aim of the research is to replace stroboscopy with HSE in conjunction with AI-based quantitative data analysis. To this end, the department publishes continuously in internationally renowned journals, presents at international conferences and collaborates with internationally renowned universities.

Prof. Dr.-Ing. M. Döllinger

Department of Phoniatrics and Paediatric Audiology

Prof. Dr. med. A. Schützenberger Prof. Dr.-Ing. M. Döllinger

Faculty of Medicine

Articles and publications

A selection of technical articles and scientific papers that have used lingWAVES.

Year

Content Type

Book recommendations voice & language

Functional laryngology: anatomy, pathophysiology, diagnostics, therapy and control of vocal function - with access to the Elsevier portal

Hardback edition April 2012 Eberhard Krusel (Author) What are the diagnostic and therapeutic concepts for various voice disorders? How efficient are they in the context of patient care and voice training? The developmental biology-based concept of functional laryngology provides you with the answers and supports you in effective therapy - clearly explained with over 200 anatomical and laryngoscopic colour illustrations.

ENT medicine, phoniatrics and paediatric audiology

2nd edition , 2021 Eichel, Hans Werner (Author) How are primary disease and speech, language, voice and swallowing disorders related? What are the aetiology, symptoms, medical diagnosis and therapy? All this knowledge has been specially compiled for the training of speech and language therapists and adapted to the curriculum. The guidelines of the medical-scientific professional associations on the respective topic are also taken into account. Learning objectives, summaries and practical excursions serve as ideal exam preparation. New in the 2nd edition: - Completely revised and updated - References to current guidelines, therapeutic and medical treatment procedures as well as the latest findings on evidence-based treatment - 55 new illustrations, even more target group-specific - Boxes for in-depth study: reference to well-founded websites at the end of each chapter / summary of important content / fact sheets on specific clinical pictures - Practical tips The book is suitable for - prospective speech therapists - prospective speech therapists

Speech therapy in neurology, geriatrics and acute rehabilitation

2nd edition, 2023 Katrin Eibl With Speech Therapy in Neurology, Geriatrics and Acute Rehabilitation you get a reference work and practical book in one! The book offers you important practice-orientated and interdisciplinary knowledge on the most important neurological speech and language disorders. You will learn about the appearance, accompanying disorders, causes, classification, diagnostics and therapy for each disorder - all taking into account the current evidence base. It also contains neuropsychological disorders relevant to speech therapy as well as increasingly important topics such as speech therapy in geriatrics or palliative care. The content is didactically organised, with many boxes on definitions, clinical background, excursuses, case studies and practical tips. Nicht zuletzt: The aim of all speech therapy is to maximise the patient's communicative participation in everyday life - this book will help you achieve this! This is what awaits you in Speech Therapy in Neurology, Geriatrics and Acute Rehabilitation:

Strongly practice-orientatedt
Diagnostics and therapy from the perspective of the speech and language therapist: when is which therapy useful and why?
Didactically valuable preparation with many heading levels, box formats for definitions, case studies, digressions, evidence-based, interdisciplinary specialities
Approx. 40 findings forms to download

Diagnostics and treatment in voice therapy

1st edition, 2024 Ben Barsties v. Latoszek, Andreas Müller, Ahmed Nasr This book describes the modern multidimensional-quantitative procedures in voice diagnostics on the basis of scientific evidence and proposes an evidence-based minimum standard in voice diagnostics. The latest scientific findings in recent years provide speech therapists, voice and speech therapists and doctors in ENT and phoniatrics with new possibilities in the medical and therapeutic care of patients with voice disorders. Voice diagnostics and the various voice treatments for heterogeneous voice disorders can thus be better interlinked in order to apply clinical reasoning for voice treatment in a structured manner. Plus: Numerous videos, audios and work materials to download make it easier to put into practice.

Experience the power of lingWAVES

Discover the Future of Voice Analysis with lingWAVES