Speaker Change Detection Based on a Weighted Distance Measure over the Centroid Model
Speaker change detection involves the identification of the time indices of an audio stream, where the identity of the speaker changes. This paper proposes novel measures for speaker change detection over the centroid model, which divides the feature space into non-overlapping clusters for effective speaker-change comparison. The centroid model is a computationally-efficient variant of the widely-used mixture-distribution based background models for speaker recognition. Experiments on both synthetic and real-world data were performed; the results show that the proposed approach yields promising results compared with the conventional statistical measures.
- IEICE transactions on information and systems
IEICE transactions on information and systems 95(5), 1543-1546, 2012-05-01