ASVspoof 5 is the fifth edition in a series of challenges which promote the study of speech spoofing and deepfake detection solutions. A significant change from previous challenge editions is a new crowdsourced database collected from a substantially greater number of speakers under diverse recording conditions, and a mix of cutting-edge and legacy generative speech technology. With the new database described elsewhere, we provide in this paper an overview of the ASVspoof 5 challenge results for the submissions of 53 participating teams. While many solutions perform well, performance degrades under adversarial attacks and the application of neural encoding/compression schemes. Together with a review of post-challenge results, we also report a study of calibration in addition to other principal challenges and outline a road-map for the future of ASVspoof.

翻译：ASVspoof 5 是该系列挑战赛的第五个版本，旨在推动语音欺骗与深度伪造检测技术的研究。相较于往届挑战赛，本次重大变革在于构建了全新的众包数据库——该库采集自数量显著增加的说话人群体，涵盖多样化的录制条件，并融合了前沿与传统的生成式语音技术。基于已另行详述的新数据库，本文系统综述了 53 支参赛团队提交方案在 ASVspoof 5 挑战赛中的表现结果。尽管多数解决方案展现出良好性能，但在对抗攻击及神经编码/压缩方案应用场景下，其性能仍出现显著下降。除回顾赛后研究成果外，本文还补充报告了校准性能研究，探讨其他核心挑战，并展望 ASVspoof 系列未来的发展路线图。