Improved binary key speaker diarization system

The recently proposed speaker diarization technique based on binary keys provides a very fast alternative to state-of-the-art systems. However, this speed up has the cost of a little increase in Diarization Error Rate (DER). This paper proposes a series of improvements to the original algorithm with the aim to get closer to state-of-the-art performance. First, several alternative similarity measures between binary key speaker/segment models are introduced. Second, we perform a first attempt at applying Intra-Session and IntraSpeaker Variability (ISISV) compensation within the binary diarization approach through the Nuisance Attribute Projection. Experimental results show the benefits of the newly introduced similarity metrics, as well as the potential of the Nuisance Attribute Projection for ISISV compensation in the binary key speaker diarization framework.