# DG^VoiC: Speaker Clustering for Fraud Investigation under Real Call-Centre Conditions

arXiv: https://arxiv.org/abs/2606.28048 · HTML: https://mlsanity.com/paper/2606.28048/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 32 references that are in the map.
- First posted on arXiv 26 Jun 2026.

## Builds on (most cited first, 7 of 7)

- [ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification](https://mlsanity.com/paper/2005.07143/) (2020)
- [WhisperX: Time-Accurate Speech Transcription of Long-Form Audio](https://mlsanity.com/paper/2303.00747/) (2023)
- [Combating Phone Scams with LLM-based Detection: Where Do We Stand?](https://mlsanity.com/paper/2409.11643/) (2024)
- [An Experimental Review of Speaker Diarization methods with application to Two-Speaker Conversational Telephone Speech recordings](https://mlsanity.com/paper/2305.18074/) (2023)
- [Real-World En Call Center Transcripts Dataset with PII Redaction](https://mlsanity.com/paper/2507.02958/) (2025)
- [AutoFraudNet: A Multimodal Network to Detect Fraud in the Auto Insurance Industry](https://mlsanity.com/paper/2301.07526/) (2023)
- [Probabilistic Back-ends for Online Speaker Recognition and Clustering](https://mlsanity.com/paper/2302.09523/) (2023)

## Abstract (arXiv)

Insurance fraud remains costly and operationally difficult, particularly in call-centre workflows where many customer interactions begin at FNOL. While recent fraud detection methods mainly rely on structured data, text, or images, repeated speaker identity across calls remains underused as an investigative signal. This paper presents DG^VoiC, a voice clustering framework for customer verification and cross-profile speaker linking on anonymised real call-centre audio. The approach combines sensitive information-aligned anonymisation, speech-focused preprocessing, sliding-window speaker embedding extraction, and cosine similarity based clustering to identify repeated speakers under real telephony conditions. The method was evaluated on 121 recordings, with a curated reference subset of 56 samples in 22 human-agreed speaker clusters. used for validation. The best configuration achieved 96% AMI, 95% ARI, 98% completeness, 100% homogeneity, and 99% V-measure. These results show that speaker clustering can provide a strong additional signal for fraud investigation by helping analysts verify speaker consistency and surface repeated voices across customers.