Scholarlink

<p>As generative artificial intelligence (AI) continues its ballistic trajectory, everything from text to audio, image, and video generation continues to improve at mimicking human-generated content. Through a series of perceptual studies, we report on the realism of AI-generated voices in terms of identity matching and naturalness. We find human participants cannot consistently identify recordings of AI-generated voices. Specifically, participants perceived the identity of an AI-generated voice to be the same as its real counterpart approximately <InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="41598_2025_94170_Article_IEq1.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="31" /> </InlineMediaObject> <EquationSource Format="TEX">\(80\%\)</EquationSource> </InlineEquation> of the time, and correctly identified a voice as AI generated only about <InlineEquation ID="IEq2"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="41598_2025_94170_Article_IEq2.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="31" /> </InlineMediaObject> <EquationSource Format="TEX">\(60\%\)</EquationSource> </InlineEquation> of the time.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

People are poorly equipped to detect AI-powered voice clones

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年3月31日

查看全文
  • Sarah Barrington,
  • Emily A. Cooper,
  • Hany Farid

摘要

As generative artificial intelligence (AI) continues its ballistic trajectory, everything from text to audio, image, and video generation continues to improve at mimicking human-generated content. Through a series of perceptual studies, we report on the realism of AI-generated voices in terms of identity matching and naturalness. We find human participants cannot consistently identify recordings of AI-generated voices. Specifically, participants perceived the identity of an AI-generated voice to be the same as its real counterpart approximately \(80\%\) of the time, and correctly identified a voice as AI generated only about \(60\%\) of the time.