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 generated 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 overlapping speech segments can be generated. The experiments show that our overlap detection method improves the performance of all three of our system configurations.
Bibliographic reference. Huijbregts, Marijn / Leeuwen, David A. van / Jong, Franciska M. G. de (2009): "Speech overlap detection in a two-pass speaker diarization system", In INTERSPEECH-2009, 1063-1066.