This paper introduces DG^VoiC, a voice clustering framework designed to identify repeated speakers in anonymized real call-center audio to assist in fraud investigation. The method combines sensitive information-aligned anonymization, speech-focused preprocessing, sliding-window speaker embedding extraction, and cosine similarity-based clustering.
- Evaluated on 121 recordings with a curated reference subset of 56 samples across 22 human-agreed speaker clusters.
- Achieved 96% AMI, 95% ARI, 98% completeness, 100% homogeneity, and 99% V-measure in the best configuration.
- Demonstrates that speaker clustering provides a strong additional signal for verifying speaker consistency and surfacing repeated voices across customers.