{
  "abstract": "VoiceGuard: An Evaluation-Honest, Multi-Signal Decision Layer for Real-Time Voice-Clone Detection in High-Stakes Telephone Calls\n\nThis paper investigates the generalization limitations of speech anti-spoofing systems for detecting voice-clone fraud in telephone calls. It examines evaluation artifacts in the ASVspoof 2019 Logical Access benchmark and re-evaluates the published AASIST model using an anti-shortcut evaluation protocol.\n\nThe paper proposes VoiceGuard, a multi-signal decision layer that combines acoustic spoof detection, speaker consistency, prosodic features, and call context to generate ALLOW, VERIFY, or ESCALATE recommendations. It also introduces a feature-only audit log to support transparency and human review.\n\nAdditionally, a five-language pilot study evaluates the transferability of an English-trained detector across Indian languages, highlighting the challenges of multilingual voice-clone detection.\n\nThe work emphasizes evaluation integrity, cross-dataset generalization, explainable decision-making, and the need for further validation before deployment in high-stakes environments.\n\nAuthors: Ghanshyam Kumavat, Sunil Saini, and Vicky Pukale\n\nAffiliation: Department of Computer Engineering, Vidyalankar Institute of Technology, Mumbai, India.",
  "abstract_shown": true,
  "affiliations": [
    "Vidyalankar Institute of Technology, Mumbai, India"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 3,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Ghanshyam Kumavat"
    },
    {
      "affs": [
        0
      ],
      "name": "Sunil Saini"
    },
    {
      "affs": [
        0
      ],
      "name": "Vicky Pukale"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/f8vz5q7n6n2b5.bib",
  "cited_by": 0,
  "doi": "10.5281/zenodo.23451734",
  "fulltext_url": null,
  "id": "f8vz5q7n6n2b5",
  "issns": [],
  "landing_url": "https://zenodo.org/records/23451734",
  "language": "eng",
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [],
  "openalex": null,
  "pdf_url": "https://zenodo.org/api/records/23451734/files/VoiceGuard_ResearchPaper_final.pdf/content",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-18",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/f8vz5q7n6n2b5.ris",
  "sources": [
    {
      "first_seen": "2026-11-01T12:21:09Z",
      "native_id": "23451734",
      "source": "zenodo",
      "url": "https://zenodo.org/records/23451734"
    }
  ],
  "subjects": [],
  "title": "VoiceGuard: An Evaluation-Honest, Multi-Signal Decision Layer for Real-Time Voice-Clone Detection in High-Stakes Telephone Calls",
  "title_text": "VoiceGuard: An Evaluation-Honest, Multi-Signal Decision Layer for Real-Time Voice-Clone Detection in High-Stakes Telephone Calls",
  "type": "preprint",
  "updated_at": "2026-11-01T12:21:09Z",
  "url": "https://research.draconitic.com/paper/f8vz5q7n6n2b5",
  "venue": "Zenodo",
  "versions": []
}