HoliAntiSpoof: 面向整体语音反伪装的音频大语言模型
HoliAntiSpoof: Audio LLM for Holistic Speech Anti-Spoofing
AI总结：
HoliAntiSpoof通过音频大语言模型实现整体语音反伪装分析，通过统一文本生成任务提升检测性能并实现可解释的语义分析。
摘要：
近期语音合成与编辑技术的发展使语音伪装变得更加困难。然而，现有大多数方法将伪装视为二元分类，忽略了多种伪装技术操控多个相互关联的语音属性及其语义影响。本文引入HoliAntiSpoof，首个面向整体语音反伪装分析的音频大语言模型（ALLM）框架。HoliAntiSpoof将伪装分析重新表述为统一的文本生成任务，实现对伪装方法、受影响的语音属性及其语义影响的联合推理。为支持语义层面分析，我们引入DailyTalkEdit，一个新的反伪装基准，模拟现实对话操控并提供语义影响的标注。广泛实验表明，HoliAntiSpoof在多个设置中均优于传统基线，初步结果表明，上下文学习进一步提升了跨领域泛化能力。这些发现表明，ALLM不仅提升了语音伪装检测性能，还实现了对伪装行为及其语义影响的可解释分析，指向更加可信和可解释的语音安全。数据和代码已公开可用。
英文摘要：
Recent advances in speech synthesis and editing have made speech spoofing increasingly challenging. However, most existing methods treat spoofing as binary classification, overlooking that diverse spoofing techniques manipulate multiple, coupled speech attributes and their semantic effects. In this paper, we introduce HoliAntiSpoof, the first audio large language model (ALLM) framework for holistic speech anti-spoofing analysis. HoliAntiSpoof reformulates spoofing analysis as a unified text generation task, enabling joint reasoning over spoofing methods, affected speech attributes, and their semantic impacts. To support semantic-level analysis, we introduce DailyTalkEdit, a new anti-spoofing benchmark that simulates realistic conversational manipulations and provides annotations of semantic influence. Extensive experiments demonstrate that HoliAntiSpoof outperforms conventional baselines across multiple settings, while preliminary results show that in-context learning further improves out-of-domain generalization. These findings indicate that ALLMs not only enhance speech spoofing detection performance but also enable interpretable analysis of spoofing behaviors and their semantic effects, pointing towards more trustworthy and explainable speech security. Data and code are publicly available.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
