Challenge Grant: Development of an Alternative Communication Tool Using Lipreading Techniques for Laryngectomy Patients

Integration

Summary

This study aims to develop a device that uses lip-reading techniques to convert video of the mouth into language, which is then converted into voice using AI synthesis. Many patients still lose their ability to speak due to treatments for laryngeal cancer and other conditions. Conventional substitute voices still have issues with clarity and sustainability. The device we are developing will solve these issues and reproduce the patient's original voice. This research will contribute to improving the quality of life for patients who have lost their ability to speak.


SDGs

3. GOOD HEALTH AND WELL-BEING3. GOOD HEALTH AND WELL-BEING
10. REDUCED INEQUALITIES10. REDUCED INEQUALITIES
11. SUSTAINABLE CITIES AND COMMUNITIES11. SUSTAINABLE CITIES AND OMMUNITIES

Project Members

About Project Members, Researchers

Note: ◎ indicates the project leader

Name Affiliation Position Field of Specialization/Research Interests
◎ Shuta Tomisato School of Medicine Instructor Otolaryngology, Speech-Language Pathology
Yasue Mitsukura Faculty of Science and Technology Professor Intelligent informatics, Kansei informatics, Electron device/Electronic equipment
Hiroyuki Ozawa School of Medicine Professor Otorhinolaryngology
Takeyuki Kono School of Medicine Assistant Professor Otolaryngology, Speech-Language Pathology
Yuta Nashimoto Faculty of Science and Technology Doctor Program Statistical Analysis
Yasuto Yada Tokyo Metropolitan University Specialist Researchers Linguistics