± SPORTS Machine learning (ML) applications continue to grow in popularity across the sport industry, offering new opp…+ LABOR As governments worldwide seek to modernise public administration through digital technologies, understanding…± HEALTH Background: Artificial intelligence (AI) is widely used in mental health care for screening, monitoring, and…± HEALTH (1) Background/Objectives: Over one billion individuals globally live with mental health conditions, yet the…± HEALTH Artificial Intelligence (AI) deployment in healthcare is accelerating, yet governance frameworks remain fragm…− HEALTH ChatGPT Health was launched in January 2026 as OpenAI's consumer health tool and has reached millions of user…+ EDUCATION This study investigates the effectiveness of AI-enhanced pedagogical practices on improving the mathematical…+ POLICY This study examined how users’ perceptions of algorithmic influence and AI manipulation are associated with k…
TruaceTracing the truth around AIMonday, July 13, 2026
Subscribe
TRV-2026-0152Certified recordPeer-reviewed

Human Detection of Voice-Cloned Speech Under GSM, VoLTE and VoIP Conditions

The rapid progress of generative speech synthesis and voice-cloning technologies has enabled the creation of highly natural synthetic voices that pose a serious threat to telecommunication security. While most prior studies evaluate human ability to detect audio deepfakes using high-quality, studio-grade recordings, little is known about how real-world telecommunication channels affect perceptual detection. This study investigates the influence of three transmission scenarios—GSM (AMR-NB), VoLTE (AMR-WB), and Vo…

Crime · The Trace — both readings · certified 2026-07-13 · v1 · article view · machine-readable

Current reading — gain

Listeners detected ElevenLabs-cloned speech more accurately when audio was transmitted through narrowband GSM (AMR-NB) at 63.7%, compared to other telecom conditions.

Current reading — problem

95 listeners could barely distinguish natural speech from ElevenLabs-cloned speech after telecom transmission, with overall accuracy of 54.8% and only 44.0% on VoLTE, increasing susceptibility to voice spoofing.

What this doesn’t fix

Findings are bounded by a small custom corpus of nine speakers and by use of simulated rather than live telecom transmission, which may not capture all real-world variability.

Evidence

Reader signal

How should this claim be treated?

Cite this record

Truvace Impact Record TRV-2026-0152, v1: “Human Detection of Voice-Cloned Speech Under GSM, VoLTE and VoIP Conditions.” Truvace, 2026-07-13. /record/TRV-2026-0152 (accessed at citation time). sha256 9ac048c232cf8341…

Calibration history

Every change to this record since certification, in the open. None yet — the reading has held since it entered the record.

  1. Certifiedv19ac048c232cf…

    Certified into the record

Verify this record
How to verify without trusting this page

Fetch the canonical text of any version from /api/record/TRV-2026-0152 and hash it yourself — for example shasum -a 256 on the saved canonical field. The result must equal content_hash, and each version’s text ends with prev:followed by the prior version’s hash (version 1 chains to 64 zeros). If a single character of any version had been altered since certification, the chain would not reproduce.