Development of multilingual medical reception support system with text-to-speech function to combine utterance data with voice synthesis

The need for multilingual communication in Japan has increased. In the medical field, there exists a serious problem when it comes to communications between hospital staff and foreign patients. Currently, medical translators accompany patients to medical care facilities, and the number of requests for medical translators is increasing. However, medical translators cannot provide support at all times, especially in cases where round-the-clock support is required or in the case of an emergency. The medical field has high expectations of information technology. We have developed a support system for multilingual medical reception called "M3." M3 provides support functions that aid foreign patients in the following respects: conversation, questionnaires, reception procedures, and hospital navigation; it also has a questions and answers function. M3 uses accurate translation tools called parallel texts to facilitate reliable communication through conversations between hospital staff and the patient. However, M3 provides text-based support, and does not provide support using voice data. We received feedback from medical interpreters that the system should provide support using voice data. Therefore, in this study, we considered the support for multilingual communication by voice data in the medical field. In this study, we propose the support system with text-to-speech function using the utterance data in combination with voice synthesis.