With the rapid advancement of technologies like text-to-speech (TTS) and voice conversion (VC), detecting deepfake voices has become increasingly crucial. However, both academia and industry lack a comprehensive and intuitive benchmark for evaluating detectors. Existing datasets are limited in language diversity and lack many manipulations encountered in real-world production environments. To fill this gap, we propose VoiceWukong, a benchmark designed to evaluate the performance of deepfake voice detectors. To build the dataset, we first collected deepfake voices generated by 19 advanced and widely recognized commercial tools and 15 open-source tools. We then created 38 data variants covering six types of manipulations, constructing the evaluation dataset for deepfake voice detection. VoiceWukong thus includes 265,200 English and 148,200 Chinese deepfake voice samples. Using VoiceWukong, we evaluated 12 state-of-the-art detectors. AASIST2 achieved the best equal error rate (EER) of 13.50%, while all others exceeded 20%. Our findings reveal that these detectors face significant challenges in real-world applications, with dramatically declining performance. In addition, we conducted a user study with more than 300 participants. The results are compared with the performance of the 12 detectors and a multimodel large language model (MLLM), i.e., Qwen2-Audio, where different detectors and humans exhibit varying identification capabilities for deepfake voices at different deception levels, while the LALM demonstrates no detection ability at all. Furthermore, we provide a leaderboard for deepfake voice detection, publicly available at {https://voicewukong.github.io}.

Meta's latest artificial intelligence model called Voicebox is a customized text to speech product that can mimic any specific voice of your choosing.

Fred, a trans man, clicked his mouse, and his tenorful tones suddenly sank deeper. He'd switched on voice-changing algorithms that provided what sounded like an instant vocal cord transplant. "This one is'Seth,'" he said, of a persona he was testing on a Zoom call with a reporter. Then, he switched to speak as "Joe," whose voice was more nasal and upbeat. Fred's friend Jane, a trans woman also testing the prototype software, chuckled and showcased some artificial voices she liked for their feminine sound.

All the sessions from Transform 2021 are available on-demand now. In 2019, Google released Translatotron, an AI system capable of directly translating a person's voice into another language. The system could create synthesized translations of voices to keep the sound of the original speaker's voice intact. But Translatotron could also be used to generate speech in a different voice, making it ripe for potential misuse in, for example, deepfakes. This week, researchers at Google quietly released a paper detailing Translatotron's successor, Translatotron 2, which solves the original issue with Translatotron by restricting the system to retain the source speaker's voice.