A Thousand Words are Worth More Than One Recording: NLP Based Speaker Change Point Detection

Abstract

Speaker Diarization (SD) consists of splitting or segmenting an input audio burst according to speaker identities. In this paper, we focus on the crucial task of the SD problem which is the audio segmenting process and suggest a solution for the Change Point Detection (CPD) problem. We empirically demonstrate the negative correlation between an increase in the number of speakers and the Recall and F1-Score measurements. This negative correlation is shown to be the outcome of a massive experimental evaluation process, which accounts its superiority to recently developed voice based solutions. In order to overcome the number of speakers issue, we suggest a robust solution based on a novel Natural Language Processing (NLP) technique, as well as a metadata features extraction process, rather than a vocal based alone. To the best of our knowledge, we are the first to tackle this variant on the SD problem (or CPD) from the intelligent NLP standpoint, and with a dataset in the Hebrew language which is an issue in its own right. We empirically show, based on two distinct datasets, that our method is abled to accurately identify the CPD's in an audio burst with 82.12% and 89.02% of success in the Recall and F1-score measurements.