CoCoEmo: 通过激活引导实现可组合且可控的类人情感语音合成
CoCoEmo: Composable and Controllable Human-Like Emotional TTS via Activation Steering
AI总结：
提出基于激活引导的框架，在混合TTS模型中实现可组合的混合情感合成和文本-情感不匹配合成，发现情感韵律主要由语言模块而非流匹配模块生成。
摘要：
人类语音中的情感表达是微妙且组合的，通常涉及多种、有时相互冲突的情感线索，这些线索可能与语言内容不一致。相比之下，大多数表现性文本转语音系统强制执行单一话语级别的情感，压缩了情感多样性并抑制了混合或文本-情感不匹配的表达。虽然通过潜在方向向量进行激活引导提供了一种有前景的解决方案，但情感表示在TTS中是否线性可引导、在混合TTS架构中应在何处应用引导以及如何评估这种复杂的情感行为仍不清楚。本文首次系统分析了混合TTS模型中用于情感控制的激活引导，引入了一个定量、可控的引导框架，以及多评估者评估协议，实现了可组合的混合情感合成和可靠的文本-情感不匹配合成。我们的结果首次证明，情感韵律和表达变异性主要由TTS语言模块而非流匹配模块合成，并提供了一种轻量级引导方法，用于生成自然、类人的情感语音。
英文摘要：
Emotional expression in human speech is nuanced and compositional, often involving multiple, sometimes conflicting, affective cues that may diverge from linguistic content. In contrast, most expressive text-to-speech systems enforce a single utterance-level emotion, collapsing affective diversity and suppressing mixed or text-emotion-misaligned expression. While activation steering via latent direction vectors offers a promising solution, it remains unclear whether emotion representations are linearly steerable in TTS, where steering should be applied within hybrid TTS architectures, and how such complex emotion behaviors should be evaluated. This paper presents the first systematic analysis of activation steering for emotional control in hybrid TTS models, introducing a quantitative, controllable steering framework, and multi-rater evaluation protocols that enable composable mixed-emotion synthesis and reliable text-emotion mismatch synthesis. Our results demonstrate, for the first time, that emotional prosody and expressive variability are primarily synthesized by the TTS language module instead of the flow-matching module, and also provide a lightweight steering approach for generating natural, human-like emotional speech.
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。
