{
  "annotation_id": "66c2f856-135a-445e-872f-4c939726c741",
  "date_created": "2026-02-17T05:53:07.509000Z",
  "date_modified": "2026-02-17T05:53:07.509000Z",
  "file_hash": "7a2d7f35546b03def0fe1ccc98e61c3418407f96ead235b34929b8a0909f1805",
  "private": false,
  "record": {
    "abstract": "We present a cost-effective two-step authentication system that integrates face identification and speaker verification using only a camera and microphone available on common devices. The pipeline first performs face recognition to identify a candidate user from a small enrolled group, then performs voice recognition only against the matched identity to reduce computation and improve robustness. For face recognition, a pruned VGG-16 based classifier is trained on an augmented dataset of 924 images from five subjects, with faces localized by MTCNN; it achieves 95.1% accuracy. For voice recognition, a CNN speaker-verification model trained on LibriSpeech (train-other-360) attains 98.9% accuracy and 3.456% EER on test-clean. Source code and trained models are available at https://github.com/NCUE-EE-AIAL/Two-step-Authentication-Multi-biometric-System.",
    "arxiv_id": "2601.06218",
    "authors": [
      "Kuan Wei Chen",
      "Ting Yi Lin",
      "Wen Ren Yang",
      "Aryan Kesarwani",
      "Riya Singh"
    ],
    "categories": [
      "cs.CV",
      "cs.AI",
      "cs.MM"
    ],
    "doi": "10.1049/icp.2024.4141",
    "journal_ref": "IET Conference Proceedings 2024 (22) 11-12 (2025)",
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "title": "Two-step Authentication: Multi-biometric System Using Voice and Facial Recognition",
    "url": "https://arxiv.org/abs/2601.06218",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "9fc516d1-690b-46dd-8259-b44840f2dd7d",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}