Metraipolis › archive › dc_2ace2a002d0b
Too Emotional to Be Fake? Intra-Utterance Emotion Shifts Expose Failure Modes in Speech Deepfake Detectors — arXiv:2610.22832
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.22832
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T08:44:04.562Z
- SHA-256 of the archived text
f325e3b2d9a5cdc5e5b181d2b1e62b0fde3ea8d50d9b838438186fa967b36930- Stable URL of this page
https://metraipolis.com/documento/dc_2ace2a002d0b
How to cite
Too Emotional to Be Fake? Intra-Utterance Emotion Shifts Expose Failure Modes in Speech Deepfake Detectors — arXiv:2610.22832 — arXiv (en), https://arxiv.org/abs/2610.22832 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2ace2a002d0b (Metraipolis archive dc_2ace2a002d0b, sha256 f325e3b2d9a5cdc5e5b181d2b1e62b0fde3ea8d50d9b838438186fa967b36930)
BibTeX
@misc{dc2ace2a002d0b,
title = {Too Emotional to Be Fake? Intra-Utterance Emotion Shifts Expose Failure Modes in Speech Deepfake Detectors — arXiv:2610.22832},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.22832},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2ace2a002d0b; sha256 f325e3b2d9a5cdc5e5b181d2b1e62b0fde3ea8d50d9b838438186fa967b36930},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22832. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Sound (cs.SD) ; Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2610.22832 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T08:39:24.899Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).