# AffectDF: The Most Comprehensive Benchmark for Speech Deepfake Detection against Emotionally Expressive Attacks arXiv: https://arxiv.org/abs/2608.05507 ยท HTML: https://mlsanity.com/paper/2608.05507/ ## Key facts - Cited by 2 papers in the map (data through 19 Oct 2026). - Placed in Anti-spoofing and adversarial audio attacks, one of 11 directions in Speech and audio language models. - Builds on 32 of its 54 references that are in the map. - First posted on arXiv 6 Aug 2026. ## Placed in - Speech and audio language models / [Anti-spoofing and adversarial audio attacks](https://mlsanity.com/speech/anti-spoofing-and-adversarial-audio-attacks/) ## Builds on (most cited first, 30 of 32) - [F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching](https://mlsanity.com/paper/2410.06885/) (2024) - [Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation](https://mlsanity.com/paper/2407.05361/) (2024) - [emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation](https://mlsanity.com/paper/2312.15185/) (2023) - [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 2021: Towards Spoofed and Deepfake Speech Detection in the Wild](https://mlsanity.com/paper/2210.02437/) (2022) - [InstructTTS: Modelling Expressive TTS in Discrete Latent Space with Natural Language Style Prompt](https://mlsanity.com/paper/2301.13662/) (2023) - [ADD 2022: the First Audio Deep Synthesis Detection Challenge](https://mlsanity.com/paper/2202.08433/) (2022) - [MLAAD: The Multi-Language Audio Anti-Spoofing Dataset](https://mlsanity.com/paper/2401.09512/) (2024) - [EmoBox: Multilingual Multi-corpus Speech Emotion Recognition Toolkit and Benchmark](https://mlsanity.com/paper/2406.07162/) (2024) - [DDDM-VC: Decoupled Denoising Diffusion Models with Disentangled Representation and Prior Mixup for Verified Robust Voice Conversion](https://mlsanity.com/paper/2305.15816/) (2023) - [XLSR-Mamba: A Dual-Column Bidirectional State Space Model for Spoofing Attack Detection](https://mlsanity.com/paper/2411.10027/) (2024) - [A Survey on Speech Deepfake Detection](https://mlsanity.com/paper/2404.13914/) (2024) - [SpoofCeleb: Speech Deepfake Detection and SASV In The Wild](https://mlsanity.com/paper/2409.17285/) (2024) - [Textless Speech Emotion Conversion using Discrete and Decomposed Representations](https://mlsanity.com/paper/2111.07402/) (2021) - [Diff-HierVC: Diffusion-based Hierarchical Voice Conversion with Robust Pitch Generation and Masked Prior for Zero-shot Speaker Adaptation](https://mlsanity.com/paper/2311.04693/) (2023) - [Laugh Now Cry Later: Controlling Time-Varying Emotional States of Flow-Matching-Based Zero-Shot Text-to-Speech](https://mlsanity.com/paper/2407.12229/) (2024) - [Advancing Zero-shot Text-to-Speech Intelligibility across Diverse Domains via Preference Alignment](https://mlsanity.com/paper/2505.04113/) (2025) - [EmoFake: An Initial Dataset for Emotion Fake Audio Detection](https://mlsanity.com/paper/2211.05363/) (2022) - [TriAAN-VC: Triple Adaptive Attention Normalization for Any-to-Any Voice Conversion](https://mlsanity.com/paper/2303.09057/) (2023) - [Expressive Voice Conversion: A Joint Framework for Speaker Identity and Emotional Style Transfer](https://mlsanity.com/paper/2107.03748/) (2021) - [Expressive-VC: Highly Expressive Voice Conversion with Attention Fusion of Bottleneck and Perturbation Features](https://mlsanity.com/paper/2211.04710/) (2022) - [GenVC: Self-Supervised Zero-Shot Voice Conversion](https://mlsanity.com/paper/2502.04519/) (2025) - [DFALLM: Achieving Generalizable Multitask Deepfake Detection by Optimizing Audio LLM Components](https://mlsanity.com/paper/2512.08403/) (2025) - [Using joint training speaker encoder with consistency loss to achieve cross-lingual voice conversion and expressive voice conversion](https://mlsanity.com/paper/2307.00393/) (2023) - [SingNet: Towards a Large-Scale, Diverse, and In-the-Wild Singing Voice Dataset](https://mlsanity.com/paper/2505.09325/) (2025) - [Towards Naturalistic Voice Conversion: NaturalVoices Dataset with an Automatic Processing Pipeline](https://mlsanity.com/paper/2406.04494/) (2024) - [NaturalVoices: A Large-Scale, Spontaneous and Emotional Podcast Dataset for Voice Conversion](https://mlsanity.com/paper/2511.00256/) (2025) - [ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks](https://mlsanity.com/paper/2604.13229/) (2026) - [Fake Speech Wild: Detecting Deepfake Speech on Social Media Platform](https://mlsanity.com/paper/2508.10559/) (2025) ## Built on by (most cited first, 2 of 2) - [Not All Attacks Are Learned Equally in Speech Deepfake Detection](https://mlsanity.com/paper/2609.11763/) (2026) - [Too Emotional to Be Fake? Intra-Utterance Emotion Shifts Expose Failure Modes in Speech Deepfake Detectors](https://mlsanity.com/paper/2610.22832/) (2026) ## Abstract (arXiv) 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.