A survey of AI-generated voices and their detection
Not on the map. Why?
Abstract (arXiv)
The ability of artificial intelligence (AI) models to generate highly realistic human voices has advanced rapidly. These technologies power accessibility tools, virtual assistants and creative applications, but they also enable harmful uses, including impersonation, fraud and disinformation. Recent incidents of voice cloning scams targeting businesses and political leaders underscore the urgent need for robust safeguards. Unlike image and video deepfakes, the detection of synthetic voices poses unique challenges due to the complexity of phonetics, prosody and auditory perception. This survey offers a comprehensive overview of AI voice generation and detection methods, encompassing both the technical foundations and the latest state-of-the-art advances. This study also identifies key open challenges, benchmark resources and future directions to make this survey useful for future researchers.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 75 of its 126 references that are in the map. First posted on arXiv 15 Aug 2026.
Builds on
75 of 126 references.
References · 75
- 2016WaveNet: A Generative Model for Raw Audiocited by 1,722
- 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,657
- 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,354
- 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 804
- 2023Neural Codec Language Models are Zero-Shot Text to Speech Synthesizerscited by 752
- 2020FastSpeech 2: Fast and High-Quality End-to-End Text to Speechcited by 717
- 2021XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scalecited by 601
- 2021Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speechcited by 561
- 2017Tacotron: Towards End-to-End Speech Synthesiscited by 490
- 2017Generalized End-to-End Loss for Speaker Verificationcited by 293
- 2018Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesiscited by 282
- 2021YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyonecited by 278
38 more
- 2020Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Searchcited by 273
- 2023NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizerscited by 235
- 2024NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Modelscited by 226
- 2019AUTOVC: Zero-Shot Voice Style Transfer with Only Autoencoder Losscited by 192
- 2021FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Datasetcited by 181
- 2021AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networkscited by 180
- 2024XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Modelcited by 179
- 2019ASVspoof 2019: Future Horizons in Spoofed and Fake Audio Detectioncited by 178
- 2018Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotroncited by 173
- 2020End-to-end anti-spoofing with RawNet2cited by 164
- 2021ASVspoof 2021: accelerating progress in spoofed and deepfake speech detectioncited by 161
- 2024MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformercited by 161
- 2022NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Qualitycited by 152
- 2023StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Modelscited by 152
- 2022ProDiff: Progressive Fast Diffusion Model For High-Quality Text-to-Speechcited by 149
- 2019MOSNet: Deep Learning based Objective Assessment for Voice Conversioncited by 127
- 2024VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizerscited by 122
- 2021Emotional Voice Conversion: Theory, Databases and ESDcited by 115
- 2018Neural Voice Cloning with a Few Samplescited by 100
- 2021AdaSpeech: Adaptive Text to Speech for Custom Voicecited by 98
- 2021Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generationcited by 93
- 2021WaveFake: A Data Set to Facilitate Audio Deepfake Detectioncited by 78
- 2024BASE TTS: Lessons from building a billion-parameter Text-to-Speech model on 100K hours of datacited by 75
- 2021End-to-End Spectro-Temporal Graph Attention Networks for Speaker Verification Anti-Spoofing and Speech Deepfake Detectioncited by 70
- 2021VQMIVC: Vector Quantization and Mutual Information-Based Unsupervised Speech Representation Disentanglement for One-shot Voice Conversioncited by 64
- 2021StarGANv2-VC: A Diverse, Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversioncited by 58
- 2019STC Antispoofing Systems for the ASVspoof2019 Challengecited by 51
- 2021PortaSpeech: Portable and High-Quality Generative Text-to-Speechcited by 47
- 2018Sample Efficient Adaptive Text-to-Speechcited by 45
- 2022DiffGAN-TTS: High-Fidelity and Efficient Text-to-Speech with Denoising Diffusion GANscited by 43
- 2023AI-Synthesized Voice Detection Using Neural Vocoder Artifactscited by 41
- 2023DDDM-VC: Decoupled Denoising Diffusion Models with Disentangled Representation and Prior Mixup for Verified Robust Voice Conversioncited by 38
- 2024CLaM-TTS: Improving Neural Codec Language Model for Zero-Shot Text-to-Speechcited by 37
- 2022Revisiting Over-Smoothness in Text to Speechcited by 32
- 2022Evidence of Vocal Tract Articulation in Self-Supervised Learning of Speechcited by 31
- 2025VITA-Audio: Fast Interleaved Cross-Modal Token Generation for Efficient Large Speech-Language Modelcited by 31
- 2025ASVspoof 5: Design, Collection and Validation of Resources for Spoofing, Deepfake, and Adversarial Attack Detection Using Crowdsourced Speechcited by 26
- 2022AVQVC: One-shot Voice Conversion by Vector Quantization with applying contrastive learningcited by 24
50 most cited of 75 All 75 (JSON)
Built on by
Not cited yet.