# Too Emotional to Be Fake? Intra-Utterance Emotion Shifts Expose Failure Modes in Speech Deepfake Detectors

arXiv: https://arxiv.org/abs/2610.22832 · HTML: https://mlsanity.com/paper/2610.22832/

## Key facts

- No citing papers in the map yet (data through 19 Oct 2026).
- Placed in Emotional speech synthesis and recognition, one of 11 directions in Speech and audio language models.
- Builds on 14 of its 28 references that are in the map.
- First posted on arXiv 16 Oct 2026.

## Placed in

- Speech and audio language models / [Emotional speech synthesis and recognition](https://mlsanity.com/speech/emotional-speech-synthesis-and-recognition/)

## Builds on (most cited first, 14 of 14)

- [XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale](https://mlsanity.com/paper/2111.09296/) (2021)
- [End-to-end anti-spoofing with RawNet2](https://mlsanity.com/paper/2011.01108/) (2020)
- [Seen and Unseen emotional style transfer for voice conversion with a new emotional speech dataset](https://mlsanity.com/paper/2010.14794/) (2020)
- [ASVspoof 5: Crowdsourced Speech Data, Deepfakes, and Adversarial Attacks at Scale](https://mlsanity.com/paper/2408.08739/) (2024)
- [XLSR-Mamba: A Dual-Column Bidirectional State Space Model for Spoofing Attack Detection](https://mlsanity.com/paper/2411.10027/) (2024)
- [Do Audio LLMs Really LISTEN, or Just Transcribe? Measuring Lexical vs. Acoustic Emotion Cues Reliance](https://mlsanity.com/paper/2510.10444/) (2025)
- [The OMG-Emotion Behavior Dataset](https://mlsanity.com/paper/1803.05434/) (2018)
- [EmoTra-TTS: Smooth Intra-Utterance Emotion Transitions for Speech Synthesis](https://mlsanity.com/paper/2608.23791/) (2026)
- [ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks](https://mlsanity.com/paper/2604.13229/) (2026)
- [Sequential Trajectories and Simultaneous Blending: Multi-Emotion Modeling for Instruction-Following TTS](https://mlsanity.com/paper/2608.30325/) (2026)
- [Why Speech Deepfake Detectors Won't Generalize: The Limits of Detection in an Open World](https://mlsanity.com/paper/2509.20405/) (2025)
- [Alethia: A Foundational Encoder for Voice Deepfakes](https://mlsanity.com/paper/2605.00251/) (2026)
- [AffectDF: The Most Comprehensive Benchmark for Speech Deepfake Detection against Emotionally Expressive Attacks](https://mlsanity.com/paper/2608.05507/) (2026)
- [The Last Mile of Deepfake Speech Detection: An Industry-Academia Experience Report](https://mlsanity.com/paper/2608.17585/) (2026)

## Abstract (arXiv)

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.