LETI: LETI Scientists Proposed a Way to Determine Individual Hearing Profile
According to the World Health Organization, more than five percent of the world’s population, about 430 million people, suffer from hearing loss. They estimate that by 2050, more than 700 million people, or one in ten, will have a disabling hearing loss.
Despite the magnitude of the problem, diagnostic and rehabilitation approaches using hearing aids are still limited. The challenge of restoring normal speech perception in everyday noise environments remains primarily due to inconsistent empirical knowledge of speech perception problems and limited individual benefits of hearing aids without systematic data analysis.
“Today, the diagnosis of hearing loss and fitting of a hearing aid relies on a non-standardized set of tests that are little related and differ from one country to another, leading to poor rehabilitation and hearing aid effectiveness. Even with a well-tuned high-tech hearing aid, patients continue to complain about speech intelligibility problems, which causes social isolation and a pronounced decrease in the quality of life,” says Maria Boboshko, member of the research team and head of the hearing and speech laboratory at Pavlov University.
The joint project “Russian-German Statistical Audiology: Data Processing and Analysis of the Audiological Profile for Diagnosis and Compensation of Hearing Loss” by scientists from LETI, Peter the Great St. Petersburg Polytechnic University, Pavlov University, and Carl von Ossietzky University of Oldenburg (Germany) will improve the rehabilitation of hearing-impaired patients based on a complete individual diagnosis of speech perception deficit and the selection and adjustment of appropriate hearing aids.
The project is led by Oleg Markelov, a leading researcher of the Digital Telecommunication Technologies Research Center at LETI, and Birger Kollmeier, Director of the Department of Medical Physics and Acoustics at the University of Oldenburg.
“The goal of the project is to apply analytical statistics and machine learning-based approaches for a better, comprehensive understanding of the patterns of functional deficits associated with hearing impairment, the suitability of various diagnostic tests, and the development of recommendations for hearing aid treatment and rehabilitation.”
Oleg Markelov, a leading researcher of the Digital Telecommunication Technologies Research Center at LETI
The final product will be a software package that will automate the hearing aid fitting process. The results of diagnostic tests and the patient’s data will be loaded into this software. Then all the information will be processed by the system, which outputs the necessary values for the fitting.
“We will create a machine-learning-based solution that will not only make the process of fitting hearing aids much easier, but will also be able to predict the effectiveness of using a hearing aid with those fittings.”
Dmitry Kaplun, Project Developer, Associate Professor of the Department of Automation and Control Processes at LETI
Now, researchers continue to analyze and collect data needed to train the system and develop diagnostic language tests, which will be invariant to the language. The project is planned for the period from 2022 to 2024. The development is supported by a grant from a joint competition of the Russian Science Foundation and the German Research Foundation (DFG).