arXiv cs.CY· Xingyu Shen, Tommy Duong, Muduo Xu, Xiaodong An, Jiaqi Gan, Haoyuan Tang, Jamey Z. Liang, Siyu Zhang, Yan Zhang, Ethan Traister, Simiao Ren·· 12 小时前AI 评分48
机器来电：测量骚扰电话中的自动化与合成语音
The Machines Are Calling: Measuring Automated and Synthetic Voices in Unwanted Inbound Calls
AI 导读
一项用语音蜜罐在66天内记录10,987通来电的研究显示，机器语音开场至少占26.9%：13.8%为在其他通话中也出现过的录音回放，13.1%为检测器判定为合成的全新音频。合成语音开场集中在获客类垃圾电话（33.8%），诈骗类为21.1%，仅0.44%披露自动化。同一波形在两次通话中有13.6%的概率落在检测器阈值的两侧，11名人工听审确认了其标记内容的54.4%。
正文
Authors:Xingyu Shen, Tommy Duong, Muduo Xu, Xiaodong An, Jiaqi Gan, Haoyuan Tang, Jamey Z. Liang, Siyu Zhang, Yan Zhang, Ethan Traister, Simiao Ren
Abstract:In February 2024 the U.S. Federal Communications Commission (FCC) placed AI-generated voices under the Telephone Consumer Protection Act (TCPA). Yet no peer-reviewed measurement says how much unwanted call traffic is placed by a machine, or how much of that machine speech is synthesized rather than played from a recording. We report both with a disclosed pipeline. An interactive voice honeypot (language-model personas on real U.S. numbers, the caller recorded on its own track) recorded 10,987 calls over 66 days. Three instruments read each opening: an audio fingerprint that finds the same recording played on other calls, a commercial synthetic-speech detector on the caller's first ten seconds, and blinded listeners who check what it flags. Of the 7,233 greeted calls we analyze, 13.8% open with a recording we also heard on another call, and 13.1% with fresh audio the detector labels synthetic. A further 9.9% open with a caller who never spoke after our greeting, 54.2% with fresh audio the detector labels human, and 9.0% could not be scored. Machine-voiced openings are therefore at least 26.9%, a further tenth of calls are silent connections we read as machine-placed, and replays of a recording make up 45% of the detector's own rate (29.3% of 6,192 scored openings). The same waveform played on two calls lands on opposite sides of the detector's threshold 13.6% of the time, and eleven listeners confirm 54.4% of what it flags. Synthetic openings concentrate in lead-generation spam (33.8%), not fraud (21.1%); 0.44% disclose automation. Prevalence tracks how long a bait number has circulated (59% against 19% in the same weeks): seeding history, not calendar time, explains the trend. Campaigns outlast their numbers: one recorded compliance notice opens calls in six campaigns, and one synthetic voice serves nine.
| Comments: | 23 pages, 11 figures, 4 tables |
| Subjects: | Cryptography and Security (cs.CR); Computers and Society (cs.CY); Sound (cs.SD) |
| Cite as: | arXiv:2609.11137 [cs.CR] |
| (or arXiv:2609.11137v3 [cs.CR] for this version) | |
| https://doi.org/10.48550/arXiv.2609.11137 arXiv-issued DOI via DataCite |
Submission history
From: Simiao Ren [view email]
[v1]
Thu, 10 Sep 2026 06:28:50 UTC (212 KB)
[v2]
Tue, 15 Sep 2026 06:38:48 UTC (203 KB)
[v3]
Sat, 24 Oct 2026 21:21:00 UTC (206 KB)
来源：arXiv cs.CY · arxiv.org