Truace
Subscribe
52/100

Moderate evidence

Cite
More
Export CSVExport JSONEmailLinkedInX

Voice-only AI spotted lies in speech with about 82% accuracy, a study of hiring talks reports

Study title: It’s not what you say, but how you say it: Using artifact intelligence to detect deception in natural speech in an HR recruiting context

Evidence type
Benchmark or lab evaluation
Sources
1 sourcePeer-reviewed
Published
2 min read
Truvace record
TRV-2026-2522cite or check it

Study title: It’s not what you say, but how you say it: Using artifact intelligence to detect deception in natural speech in an HR recruiting context

Researchers built an AI tool that analyzes only the human voice, using natural language processing, to judge whether a speaker is stating their true conviction. It detects deceptive statements with about 82% accuracy, according to the paper in the Journal of Information Technology.

Read the study abstract

Human emotions trigger physical reactions of the body that can be interpreted using artificial intelligence (AI) methods. AI-enabled detection mechanisms offer new opportunities to gain deeper understanding of human emotions. AI is already able to recognize basic emotions, such as joy, anger, or fear, but is challenged to detect complex emotions accurately, such as when someone is lying. The human voice conveys a wealth of subconscious information. This research utilizes natural language processing (NLP) to pres…

The gain

A study reports that a voice-only AI tool flagged deceptive statements with about 82% accuracy, aimed at helping HR staff who are naturally weak at spotting lies in recruitment talks.

In brief

The authors propose corporate recruitment as a use case, describing it as an area where people traditionally lie a lot and where HR staff are naturally weak at detecting deception. They say the tool could help managers decide better.

The design aims to suit sensitive hiring conversations: it has no speech recognition and stores no information that identifies the speaker. The authors add that such tools will challenge theories of organizational decision making as human–AI hybrids emerge.

Main points

  1. The tool analyzes only the human voice to judge whether a speaker is stating their true conviction.
  2. It detects deceptive statements with about 82% accuracy.
  3. The authors frame corporate recruitment as a suitable use case, where people traditionally lie a lot.
  4. The tool is meant to support HR staff, whom the authors describe as naturally weak at detecting deception.
  5. For privacy, it has no speech recognition capability and does not store information identifying the speaker.
  6. The authors say AI can already recognize basic emotions such as joy, anger or fear but struggles with complex ones such as lying.

The full story

The study, published in the Journal of Information Technology in June 2026, presents what the authors call a novel AI artifact built with natural language processing. It works from the human voice alone to assess whether a person is speaking according to their true conviction.

The authors position it for decision makers who need to know whether someone's arguments are truthful, with recruitment as the main example. They argue the tool could help HR staff make better decisions and let managers more accurately detect deceptive behavior of interview partners.

Privacy shaped the design: the tool cannot transcribe speech and does not keep data that identifies speakers. The authors conclude that using AI to compensate for humans' weak ability to detect complex emotions will challenge how organizational decision making is conceptualized.

Sources

1 on file
  1. Journal of Information Technologydoi:10.1177/02683962261462966
    Peer-reviewed2026-06-10

Talk it over

Four questions to start onWho gets this benefit, and who was left out of the study or story?

Start with a question

Voice-only AI spotted lies in speech with about 82% accuracy, a study of hiring talks reportshttps://truvace.com/item/its-not-what-you-say-but-how-you-say-it-using-artifact-intelligence-to-detect-de

  1. Who gets this benefit, and who was left out of the study or story?

    The gain A study reports that a voice-only AI tool flagged deceptive statements with about 82% accuracy, aimed at helping HR staff who are naturally weak at spotting lies in recruitment talks.

    Answer in the thread

  2. How do we know? What can this kind of evidence show, and what can’t it?

    The evidence This rests on a benchmark or lab test, from Journal of Information Technology.

    Answer in the thread

  3. What does it leave open? What else would you want to know before acting on it?

    Answer in the thread

  4. Have you seen AI used this way where you study, work or live? Did it go the same way?

    Answer in the thread

The questions are the same on every record. The details under them are taken from this record as written.

What readers say

More from Business