This paper proposes an automatic foreground segmentation system based on Gaussian mixture models and dynamic graph cut algorithm. An adaptive perpixel background model is develope...
While clustering is usually an unsupervised operation, there are circumstances in which we believe (with varying degrees of certainty) that items A and B should be assigned to the...
Background subtraction is commonly used to detect foreground objects in video surveillance. Traditional background subtraction methods are usually based on the assumption that the...
We propose a novel feature set for speaker recognition that is based on the voice source signal. The feature extraction process uses closed-phase LPC analysis to estimate the voca...
The TNO speaker speaker diarization system is based on a standard BIC segmentation and clustering algorithm. Since for the NIST Rich Transcription speaker dizarization evaluation m...