Automatic Speaker Recognition (ASR): Application in the monitoring of PLHIV in the cross-border area between the Gambia, Guinea-Bissau and Senegal

Abstract

This article focuses on the study and optimization of the monitoring system for People Living with HIV (PLWHIV) in the cross-border area between the Gambia, Senegal and Guinea Bissau. Difficulties in adherence to treatment are accentuated, among other things, by the stigmatization of HIV patients and the high mobility of the population. These two situations and the absence of a reliable identification system for PLWHIV lead to restarting treatment for certain patients, which can cause resistance. This article presents the problem of automatic speaker recognition in the monitoring of PLWHA to avoid resumption of treatment and reduce the number of patients on ART lost to removing duplicates of patients in follow-up. From the technical point of view, we presented the problem of identification by speech. We proposed a state of the arts pretty full on art methodology s existing. We proposed a model with a first implementation allowing to make the first analyzes. We also presented a set of related works.