A new database of healthy and pathological voices

In the era of Edge-of-Things computing for the accomplishment of smart healthcare systems, the availability of accurate and reliable databases is important to provide the right tools for researchers and business companies to design, develop and test new techniques, methodologies and/or algorithms to monitor or detect the patient's healthcare status. In this paper, the study and building of the VOice ICar fEDerico II (VOICED) database are presented, useful for anybody who needs voice signals in her/his research activities. It consists of 208 healthy and pathological voices collected during a clinical study performed following the guidelines of the medical SIFEL (Società Italiana di Foniatria e Logopedia) protocol and the SPIRIT (Standard Protocol Items: Recommendations for Interventional Trials) 2013 Statement. For each subject, the database contains a recording of the vowel /a/ of five seconds in length, lifestyle information, the medical diagnosis, and the results of two specific medical questionnaires.