Abstract

Agglomerative hierarchical clustering (AHC) has been widely used in speaker diarization systems to classify speech segments in a given data source by speaker identity, but is known to be not robust to data source variation. In this paper, we identify one of the key potential sources of this variability that negatively affects clustering error rate (CER), namely short speech segments, and propose three solutions to tackle this issue. Through experiments on various meeting conversation excerpts, the proposed methods are shown to outperform simple AHC in terms of relative CER improvements in the range of 17-32%.

Date

2007

Authors

Kyu J Han, Samuel Kim, Shrikanth S Narayanan

Conference

2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)

Pages

262-267

Publisher

IEEE