Speech overlap detection in a two-pass speaker diarization system

In this paper we present the two-pass speaker diarization system that we developed for the NIST RT09s evaluation. In the first pass of our system a model for speech overlap detection is gen­ erated automatically. This model is used in two ways to reduce the diarization errors due to overlapping speech. First, it is used in a second diarization pass to remove overlapping speech from the data while training the speaker models. Second, it is used to find speech overlap for the final segmentation so that overlap­ ping speech segments can be generated. The experiments show that our overlap detection method improves the performance of all three of our system configurations.