The Influence of Speech/Non-Speech Segmentation on On-Line and Off-Line Speaker Segmentation Accuracy

The paper analyses the influence of speech/non-speech segmentation on on-line and off-line speaker segmentation accuracy. On-line and off-line speaker segmentation approaches together with speaker diarization are shortly reviewed and popular "state of the art" test systems are presented. Both systems are tested on a given test set with and without speech/non-speech segmentation. A conclusion on on-line and off-line segmentation performance is given at the end. Experiments and test evaluation are performed on the Slovenian BNSI Broadcast News speech database. The experimental results have shown a high influence of speech/non-speech segmentation on both on-line and off-line segmentation accuracy.