Active correction for speaker diarization with human in the loop

Yevhenii Prokopalo, Meysam Shamsi, Loic Barrault, Sylvain Meignier, Anthony Larcher

State of the art diarization systems now achieve decent perfor-mance but those performances are often not good enough to deploy them without any human supervision. In this paper wepropose a framework that solicits a human in the loop to correct the clustering by answering simple questions. After defining the nature of the questions, we propose an algorithm to listthose questions and two stopping criteria that are necessary to limit the work load on the human in the loop. Experiments performed on the ALLIES dataset show that a limited interaction with a human expert can lead to considerable improvement of up to 36.5% relative DER compared to a strong baseline.

doi: 10.21437/IberSPEECH.2021-55

Prokopalo, Y, Shamsi, M, Barrault, L, Meignier, S, Larcher, A (2021) Active correction for speaker diarization with human in the loop. Proc. IberSPEECH 2021, 260-264, doi: 10.21437/IberSPEECH.2021-55.