Evaluating Human Corrections in a Computer-Assisted Speaker Diarization System

In this paper, we present a framework to evaluate the human corrections of a speaker diarization system. We propose four elementary actions to correct the diarization (“ Create a boundary ”, “ Delete a boundary ”, “ Create a speaker label ” and “ Change the speaker label ”) and we propose an automaton to simulate the correction sequence. A metric is described to evaluate the correction cost. The framework is evaluated using French broadcast news drawn from the following campaigns: REPERE, ESTER and ETAPE.