什么让合成语音听起来讽刺？一项韵律控制的感知研究
What Makes Synthetic Speech Sound Sarcastic? A Prosody-Controlled Perception Study
AI总结：
通过可控神经TTS系统操纵语速、音高变化和响度，发现响度主要驱动人类对讽刺的感知，而模型更依赖语速，揭示了韵律线索权重差异。
摘要：
韵律在讽刺感知中起着核心作用，然而以往的研究依赖于自然产生的语音，缺乏对单个声学维度的精细控制。由于韵律线索在自然数据中共变，隔离它们的独立贡献仍然具有挑战性。我们引入了一个受控框架，使用基于提示的韵律条件化的神经文本到语音（TTS）来操纵语速、音高变化和响度。构建了一个正交刺激集，以实现对韵律线索效应的因果测试。人类听众对讽刺性和自然度进行评分，并将他们的判断与能够处理音频输入的基础模型的预测进行比较。结果表明，响度主要驱动人类对讽刺的感知，而模型则赋予语速更大的权重，导致不同的线索加权模式。这项研究表明，可控神经TTS如何能够研究语音感知中的韵律线索加权。
英文摘要：
Prosody plays an important role in sarcasm perception, yet previous studies have relied on naturally produced speech that lacks fine-grained control over individual acoustic dimensions. As prosodic cues co-vary in natural data, isolating their independent contributions remains challenging. We introduce a controlled framework using neural text-to-speech (TTS) with prompt-based prosodic conditioning to manipulate speech rate, pitch variation, and loudness. An orthogonal stimulus set was constructed to enable causal testing of prosodic cue effects. Human listeners rated sarcasm and naturalness, and their judgments were compared with predictions from a foundation model capable of processing audio input. Results show that loudness primarily drives human sarcasm perception, whereas the model assigns greater weight to speech rate, indicating limited behavioral alignment. This study shows how controllable neural TTS enables investigation of prosodic cue weighting in speech perception.
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。
