Metraipolis › archive › dc_0ef823e33e8a
Before the Warning Comes Too Late: Incremental Phone-Scam Detection from Speech — arXiv:2609.20223
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.20223
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-10T03:48:15.850Z
- SHA-256 of the archived text
5c538cccb66ee05b46e6e118c0b09cc14741de12869e627e177a7b31c29bde77- Stable URL of this page
https://metraipolis.com/documento/dc_0ef823e33e8a
How to cite
Before the Warning Comes Too Late: Incremental Phone-Scam Detection from Speech — arXiv:2609.20223 — arXiv (en), https://arxiv.org/abs/2609.20223 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0ef823e33e8a (Metraipolis archive dc_0ef823e33e8a, sha256 5c538cccb66ee05b46e6e118c0b09cc14741de12869e627e177a7b31c29bde77)
BibTeX
@misc{dc0ef823e33e8a,
title = {Before the Warning Comes Too Late: Incremental Phone-Scam Detection from Speech — arXiv:2609.20223},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.20223},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0ef823e33e8a; sha256 5c538cccb66ee05b46e6e118c0b09cc14741de12869e627e177a7b31c29bde77},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.20223. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We study weakly supervised incremental telecom fraud detection from raw telephone audio, where training provides only conversation-level labels and predictions must be updated before a call ends. We introduce StreamFraudNet, which processes incoming audio through overlapping bounded-context windows using a frozen self-supervised speech encoder, recurrent temporal modeling, and learned aggregation of latent window scores. On a controlled English benchmark, StreamFraudNet achieves a ROC--AUC of \(0.9953\), significantly outperforming acoustic and mean-pooling baselines while remaining competitive with strong global temporal models. The model produces its first prediction after 10 seconds of audio, updates every 2 seconds, and operates faster than real time on the evaluated server hardware. Ablations identify recurrent temporal context as the principal contributor to performance. These results demonstrate that fraud risk can be scored incrementally from raw speech without transcripts or temporal annotations, while highlighting the need for latency-aware training to improve early prediction. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-18 in cs.CL). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.20223 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-10T03:24:08.154Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).