HuLA：面向表现力与情感合成语音的韵律感知多任务学习防欺骗
HuLA: Prosody-Aware Anti-Spoofing with Multi-Task Learning for Expressive and Emotional Synthetic Speech
AI总结：
本文提出HuLA，一种两阶段韵律感知多任务学习框架，通过SSL骨干网络和韵律辅助任务提升防欺骗系统对表现力与情感合成语音的检测鲁棒性，实验证明其在跨域攻击上优于强基线。
摘要：
当前的防欺骗系统在面对表现力丰富和情感化的合成语音时仍然脆弱，因为它们很少利用韵律作为判别性线索。韵律是人类表现力和情感的核心，人类本能地使用韵律线索（如F0模式和清音/浊音结构）来区分自然语音与合成语音。在本文中，我们提出了HuLA，一个两阶段的韵律感知多任务学习框架，用于欺骗检测。在第一阶段，一个自监督学习（SSL）骨干网络在真实语音上通过辅助任务（F0预测和清音/浊音分类）进行训练，增强其捕捉自然韵律变化的能力，类似于人类感知学习。在第二阶段，模型在真实和合成数据上联合优化欺骗检测和韵律任务，利用韵律感知来检测自然语音与表现力合成语音之间的不匹配。实验表明，HuLA在具有挑战性的跨域数据集上持续优于强基线，包括表现力、情感和跨语言攻击。这些结果表明，显式的韵律监督结合SSL嵌入，显著提高了对高级合成语音攻击的鲁棒性。
英文摘要：
Current anti-spoofing systems remain vulnerable to expressive and emotional synthetic speech, since they rarely leverage prosody as a discriminative cue. Prosody is central to human expressiveness and emotion, and humans instinctively use prosodic cues such as F0 patterns and voiced/unvoiced structure to distinguish natural from synthetic speech. In this paper, we propose HuLA, a two-stage prosody-aware multi-task learning framework for spoof detection. In Stage 1, a self-supervised learning (SSL) backbone is trained on real speech with auxiliary tasks of F0 prediction and voiced/unvoiced classification, enhancing its ability to capture natural prosodic variation similar to human perceptual learning. In Stage 2, the model is jointly optimized for spoof detection and prosody tasks on both real and synthetic data, leveraging prosodic awareness to detect mismatches between natural and expressive synthetic speech. Experiments show that HuLA consistently outperforms strong baselines on challenging out-of-domain dataset, including expressive, emotional, and cross-lingual attacks. These results demonstrate that explicit prosodic supervision, combined with SSL embeddings, substantially improves robustness against advanced synthetic speech attacks.
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。
