English

Detecting the Undetectable: Assessing the Efficacy of Current Spoof Detection Methods Against Seamless Speech Edits

Sound 2025-01-08 v1 Computation and Language Audio and Speech Processing

Abstract

Neural speech editing advancements have raised concerns about their misuse in spoofing attacks. Traditional partially edited speech corpora primarily focus on cut-and-paste edits, which, while maintaining speaker consistency, often introduce detectable discontinuities. Recent methods, like A\textsuperscript{3}T and Voicebox, improve transitions by leveraging contextual information. To foster spoofing detection research, we introduce the Speech INfilling Edit (SINE) dataset, created with Voicebox. We detailed the process of re-implementing Voicebox training and dataset creation. Subjective evaluations confirm that speech edited using this novel technique is more challenging to detect than conventional cut-and-paste methods. Despite human difficulty, experimental results demonstrate that self-supervised-based detectors can achieve remarkable performance in detection, localization, and generalization across different edit methods. The dataset and related models will be made publicly available.

Keywords

Cite

@article{arxiv.2501.03805,
  title  = {Detecting the Undetectable: Assessing the Efficacy of Current Spoof Detection Methods Against Seamless Speech Edits},
  author = {Sung-Feng Huang and Heng-Cheng Kuo and Zhehuai Chen and Xuesong Yang and Chao-Han Huck Yang and Yu Tsao and Yu-Chiang Frank Wang and Hung-yi Lee and Szu-Wei Fu},
  journal= {arXiv preprint arXiv:2501.03805},
  year   = {2025}
}

Comments

SLT 2024