mlsanityData to 14 Oct 2026

Can Emotion Fool Anti-spoofing?

arXiv 2505.23962 ↗First posted 29 May 2025eess.AS cs.LG cs.SDcited by 4

Not on the map. Why?

Abstract (arXiv)

Traditional anti-spoofing focuses on models and datasets built on synthetic speech with mostly neutral state, neglecting diverse emotional variations. As a result, their robustness against high-quality, emotionally expressive synthetic speech is uncertain. We address this by introducing EmoSpoof-TTS, a corpus of emotional text-to-speech samples. Our analysis shows existing anti-spoofing models struggle with emotional synthetic speech, exposing risks of emotion-targeted attacks. Even trained on emotional data, the models underperform due to limited focus on emotional aspect and show performance disparities across emotions. This highlights the need for emotion-focused anti-spoofing paradigm in both dataset and methodology. We propose GEM, a gated ensemble of emotion-specialized models with a speech emotion recognition gating network. GEM performs effectively across all emotions and neutral state, improving defenses against spoofing attacks. We release the EmoSpoof-TTS Dataset: https://emospoof-tts.github.io/Dataset/

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 19 of its 27 references that are in the map. First posted on arXiv 29 May 2025.

Builds on

19 of 27 references.

References · 19

  1. 2023Neural Codec Language Models are Zero-Shot Text to Speech Synthesizerscited by 752
  2. 2023Voicebox: Text-Guided Multilingual Universal Speech Generation at Scalecited by 379
  3. 2024F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matchingcited by 361
  4. 2024CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokenscited by 334
  5. 2021AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networkscited by 180
  6. 2020End-to-end anti-spoofing with RawNet2cited by 164
  7. 2023StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Modelscited by 152
  8. 2020Seen and Unseen emotional style transfer for voice conversion with a new emotional speech datasetcited by 121
  9. 2022ASVspoof 2021: Towards Spoofed and Deepfake Speech Detection in the Wildcited by 121
  10. 2022ADD 2022: the First Audio Deep Synthesis Detection Challengecited by 96
  11. 2024ASVspoof 5: Crowdsourced Speech Data, Deepfakes, and Adversarial Attacks at Scalecited by 91
  12. 2021Deepfakes Generation and Detection: State-of-the-art, open challenges, countermeasures, and way forwardcited by 82
7 more
  1. 2023ADD 2023: the Second Audio Deepfake Detection Challengecited by 64
  2. 2022EmoDiff: Intensity Controllable Emotional Text-to-Speech with Soft-Label Guidancecited by 37
  3. 2023PromptTTS++: Controlling Speaker Identity in Prompt-Based Text-to-Speech Using Natural Language Descriptionscited by 25
  4. 2019ASSERT: Anti-Spoofing with Squeeze-Excitation and Residual neTworkscited by 23
  5. 2020Light Convolutional Neural Network with Feature Genuinization for Detection of Synthetic Speech Attackscited by 23
  6. 2022EmoFake: An Initial Dataset for Emotion Fake Audio Detectioncited by 10
  7. 2024ED-TTS: Multi-Scale Emotion Modeling using Cross-Domain Emotion Diarization for Emotional Speech Synthesiscited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 2.

4 papers.

  1. 2025NaturalVoices: A Large-Scale, Spontaneous and Emotional Podcast Dataset for Voice Conversioncited by 2
  2. 2026Alethia: A Foundational Encoder for Voice Deepfakescited by 1
  3. 2025HuLA: Prosody-Aware Anti-Spoofing with Multi-Task Learning for Expressive and Emotional Synthetic Speechcited by 0
  4. 2026I Hear, Therefore I Trust: A Socio-Technical Investigation of Humans as Synthetic Speech Detectorscited by 0