arXiv cs.CL· Jingyi Chen, Surya Koppisetti·· 12 小时前AI 评分32
EmoShift 基准揭示：语句内情感变化会让语音深伪检测器漏检率最高上升 25.3 个百分点
Too Emotional to Be Fake? Intra-Utterance Emotion Shifts Expose Failure Modes in Speech Deepfake Detectors
AI 导读
研究团队提出 EmoShift 基准，用 7,240 条真实语音和 4 种表达性 TTS 系统生成的 9,720 条合成语音，对比情感稳定（AA）与情感变化（AB）语音对深伪检测的影响。
正文 · 原文
Abstract:Expressive speech synthesis can now change emotion within a single utterance, yet its impact on deepfake detection remains unclear. We introduce EmoShift, a benchmark comparing emotion-stable (AA) and emotion-changing (AB) speech to examine these effects while accounting for static emotion identity and acoustic confounds. It comprises 7,240 bona fide utterances from four source datasets and 9,720 synthetic utterances generated using four expressive TTS systems. Across seven detectors, we find that emotion changes can make synthetic speech appear more genuine, increasing spoof miss rates by up to 25.3 percentage points on OMG-Emotion at fixed thresholds. Conversely, emotion-changing bona fide speech increases false-alarm rates by up to 24.4 percentage points on IEMOCAP. Further analyses reveal detector-specific sensitivities to emotion trajectories, not fully explained by static emotion identity or splicing artifacts. These findings underscore the importance of emotion dynamics in deepfake detection.
| Comments: | Preprint. Under review |
| Subjects: | Sound (cs.SD); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.22832 [cs.SD] |
| (or arXiv:2610.22832v1 [cs.SD] for this version) | |
| https://doi.org/10.48550/arXiv.2610.22832 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jingyi Chen [view email]
[v1]
Fri, 16 Oct 2026 02:19:40 UTC (140 KB)
来源：arXiv cs.CL · arxiv.org