The project won the competitive selection for the “Start” program of the Foundation for Assistance to Small Innovative Enterprises in the Scientific and Technical Field
The correct pronunciation of various sounds of speech depends on the articulation of a person, determined by the position of his lips and tongue. Nowadays only a speech therapist can follow this, constantly monitoring these parameters when working with people with speech disorders.
The scientists of Vyatka State University proposed to simplify this process and make it more effective. They developed a methodology for analyzing articulation and combined it with a solution for recognizing sound in the framework of an artificial intelligence system.
For more than a year, the Flagship University of the Kirov region has been conducted studies, aimed at developing a speech rehabilitation system for patients with neurological and maxillofacial pathology based on artificial intelligence.
The project team, who became the winner of competitive selection for the “Start” program of the Foundation for Assistance to Small Innovative Enterprises in the Scientific and Technical Field in the direction “H2. Medicine and health protection technologies”, included scientists, speech pathologists and programmers of VyatSU.
The program we create will evaluate the image from the camera, determining how the patient sets his lips and tongue when pronouncing any sound or syllable,
said the Dean of the Faculty of Pedagogy and Psychology of the Pedagogical Institute of VyatSU Vyacheslav Utemov. -
At the same time, the program will record and recognize the resulting sound and compare it with a predetermined ideal pattern, evaluating the quality of speech.
