This work introduces AffectDF, the most comprehensive benchmark for emotionally expressive speech deepfakes, spanning TTS, VC, emotional VC, and LALM-based spoofing attacks across both acted and spontaneous emotional speech.
Abstract
Speech deepfake detection (SDD) systems achieve strong performance on conventional benchmarks; however, existing datasets provide limited coverage of emotionally expressive and recent large audio-language model (LALM)-based attacks. Existing emotional spoofing datasets are also limited in scale and attack diversity, typically covering only voice conversion (VC) or text-to-speech (TTS) attacks. We introduce AffectDF, the most comprehensive benchmark for emotionally expressive speech deepfakes, spanning TTS, VC, emotional VC, and LALM-based spoofing attacks across both acted and spontaneous emotional speech. AffectDF contains approximately 260 hours of speech generated using 21 spoofing attacks across five emotional states. We benchmark state-of-the-art SDD systems under conventional and emotional spoofing conditions, including LALM-based detectors evaluated with both inference-only prompting and supervised fine-tuning. Our experiments reveal severe robustness degradation when models trained on conventional benchmarks are evaluated on AffectDF, with several systems approaching near-random performance. Surprisingly, even large-scale emotional training does not consistently improve cross-domain robustness, indicating that current SDD systems fail to learn generalized spoof representations under emotional and prosodic variability. Robustness further varies substantially across emotional states, attack families, and acted vs spontaneous emotional speech conditions. These findings expose fundamental limitations of current SDD systems and establish AffectDF as a benchmark for developing more robust spoof detection models.
The increasing prevalence of spoofing attacks in automatic speaker verification systems underscores the critical need for robust detection methods to ensure security and reliability. Although current spoof speech datasets primarily focus on synthesized speech and voice conversion attacks, human-imitated speech remains...
Khalid Zaman, Kai Li, Anuwat Chaiwongyen et al.· IEEE Access· 0 citations
A replay-regularized, attack-aware curriculum that steps exposure based on measured attack influence is proposed that shows improved overall robustness and reduced attack-level imbalance compared with standard multi-attack training.
Avantika Singh, Aurosweta Mahapatra, I. R. Ulgen et al.· 0 citations
The results indicate that multi-domain feature fusion offers a practical and generalizable solution for real-world deepfake audio detection, particularly in environments involving diverse codecs and synthesis techniques.
Akshat Chhatriwala, Ishita Akolkar, Namrata Shroff et al.· ITEGAM- Journal of Engineeri...· 0 citations
EMBNet is proposed, a task-oriented deepfake speech detection framework that integrates efficient channel attention (ECA) with a multi-scale bottleneck to enhance the representation of subtle acoustic anomalies and may support forensic audio authenticity assessment by improving the discrimination between genuine and ma...
Haitao Yang, Fen Li, Xin Cai et al.· Journal of Forensic Sciences· 0 citations
The results show that the evaluated baselines can extract some affective signal from speech, but discrete expressed-emotion recognition remains fragile, especially for non-neutral emotions that are often most important in voice agent workflows.
Luc Debaupte, Tyler Baumgartner, Brandon Tai et al.· 1 citation
Rapid advances in text-to-speech (TTS) and voice conversion (VC) have substantially lowered the barrier to generating zero-shot spoofed speech, posing critical challenges for identity authentication, media forensics, and speech security. Current audio deepfake detection methods typically employ large-scale self-supervi...